Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
Explainable Inference Over Grounding-Abstract Chains for Science Questions (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing inference models for science questions are black-box by nature, lacking explanations for their predictions. |
| Approach: | They propose an explainable inference approach for science questions by reasoning on grounding and abstract inference chains. |
| Outcome: | The proposed model generates plausible explanations for science questions using a weighted graph of relevant facts and a Bayesian Optimisation formalism. |
LV-BERT: Exploiting Layer Variety for BERT (2021.findings-acl)
Copied to clipboard
| Challenge: | Modern pre-trained language models are mostly built upon stereotyped development sets . LV-BERT model obtained by our method outperforms BERT on various downstream tasks . |
| Approach: | They propose to exploit layer variety from the layer type set and the layer order to improve pre-trained models. |
| Outcome: | The proposed model outperforms BERT and its variants on various downstream tasks. |
Few-Shot Event Detection with Prototypical Amortized Conditional Random Field (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to event detection ignore the trigger discrepancy and cause errors. |
| Approach: | They propose a unified model which converts a few-shot tagging problem into a single-shot model by using a Gaussian distribution. |
| Outcome: | The proposed model performs better than existing identifythen-classify models on a few-shot tagging problem with a double-part taging scheme. |
LUX (Linguistic aspects Under eXamination): Discourse Analysis for Automatic Fake News Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Automated fact-checking is time-consuming and cannot scale due to a lack of suitable training data. |
| Approach: | They propose to use a dataset to automatically check facts and a text classifier to infer the likelihood of the input being a piece of fake-news. |
| Outcome: | The proposed dataset VERITAS and LUX use linguistic analysis to infer the likelihood of the input being a piece of fake-news. |
Diagnosing Transformers in Task-Oriented Semantic Parsing (2021.findings-acl)
Copied to clipboard
| Challenge: | a recent study shows transformer-based parsers struggle with disambiguating intents/slots and producing syntactically valid frames. |
| Approach: | They propose to use seq2seq transformers to map textual utterances to semantic frames . they propose to model transformer-based parsers across monolingual and multilingual settings . |
| Outcome: | The proposed parsers struggle with disambiguating intents/slots and produce syntactically valid frames. |
Semantic Relation-aware Difference Representation Learning for Change Captioning (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to describe semantic change in images with distractors are difficult to learn . |
| Approach: | They propose a semantic relation-aware difference representation learning network to explicitly learn the difference representation in the existence of distractors. |
| Outcome: | The proposed network achieves state-of-the-art performance on CLEVR-Change and Spot-the -Diff datasets. |
The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on text classification have focused on the bias towards the individuals mentioned in the text content. |
| Approach: | They propose a framework to mitigate implicit bias in text classification models based on demographic attributes of authors . they propose to use this framework to train deep text classifiers to make predictions on the right features . |
| Outcome: | The proposed framework outperforms existing models significantly in fairness and performance. |
From What to Why: Improving Relation Extraction with Rationale Graph (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing neural relation extraction models are limited by entity type and textual context. |
| Approach: | They propose a novel RAtionale Graph to organize co-occurrence constraints among entity types, triggers and relations in a holistic graph view. |
| Outcome: | The proposed method outperforms baselines significantly and achieves state-of-the-art performance on document-level and sentence-level RE benchmarks. |
More Parameters? No Thanks! (2021.findings-acl)
Copied to clipboard
| Challenge: | Using network pruning, we find that there are large redundancies in MNMT models. |
| Approach: | They propose a method to prune and retrain redundant parameters of an MNMT model to improve bilingual representations while retaining multilinguality. |
| Outcome: | The proposed method improves bilingual representations while retaining multilinguality. |
SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models have limitations to generalize to diverse semantic phenomena, and it is unclear whether they can capture compositional meanings. |
| Approach: | They propose a systematic generalization testbed based on Natural language semantics to map natural language sentences to multiple meaning representations. |
| Outcome: | The proposed model can generalize to unseen combinations of quantifiers, negations, and modifiers, but not to the others. |
Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing non-autoregressive neural machine translation models are slow to learn the dependency between output tokens. |
| Approach: | They propose to use fully non-autoregressive neural machine translation (NAT) to predict tokens with single forward of neural networks. |
| Outcome: | The proposed model achieves state-of-the-art results on three translation benchmarks with comparable performance to autoregressive and iterative NAT systems. |
Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech (2021.findings-acl)
Copied to clipboard
| Challenge: | Off-the-shelf methods to generate hate speech are limited in that they generate repetitive and safe responses regardless of the hate speech. |
| Approach: | They propose a three-module pipeline approach to generate diverse and relevant counterspeech . they first generate various counterspeak candidates by a generative model, then filter ungrammatical ones using a BERT model . |
| Outcome: | The proposed pipeline generates diverse and relevant counterspeech responses on three datasets. |
REPT: Bridging Language Models and Machine Reading Comprehension via Retrieval-Based Pre-training (2021.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models have achieved great success on Machine Reading Comprehension (MRC) however, the poor support in evidence extraction hinders them from further advancing MRC. |
| Approach: | They propose a REtrieval-based pre-training approach that strengthens evidence extraction during pre-training by inherited downstream MRC tasks. |
| Outcome: | The proposed approach strengthens evidence extraction during pre-training, which is further inherited by downstream tasks. |
CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods assume that events appear in sentences without overlaps . overlapping event extraction is a challenging task in natural language understanding . |
| Approach: | They propose a joint learning framework with cascade decoding for overlapping event extraction . they sequentially perform type detection, trigger extraction and argument extraction based on the specific former prediction . |
| Outcome: | The proposed framework improves on a public event extraction benchmark . it sequentially performs type detection, trigger extraction and argument extraction . |
Discovering Topics in Long-tailed Corpora with Causal Intervention (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing topic models are designed and evaluated on balanced corpora, but the longtailed bias can impair the performance of topic models. |
| Approach: | They propose a causal inference framework to explain topic modeling on long-tailed corpora by applying causal intervention in training. |
| Outcome: | The proposed model can mitigate the bias effect, greatly improve topic quality and discover the hidden semantics on the tail. |
More than just Frequency? Demasking Unsupervised Hypernymy Prediction Methods (2021.findings-acl)
Copied to clipboard
| Challenge: | Using unsupervised methods of hypernymy prediction, we show that the predictions of three methods overlap and are highly correlated with frequency-based predictions. |
| Approach: | They compare unsupervised methods of hypernymy prediction to supervised methods . they show that the methods overlap and are highly correlated with frequency-based predictions . |
| Outcome: | The proposed methods overlap and are highly correlated with frequency-based predictions across English and German datasets. |
WikiTableT: A Large-Scale Data-to-Text Dataset for Generating Wikipedia Article Sections (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing datasets for data-to-text generation focus on single-sentence generation or long-form generation. |
| Approach: | They create a dataset that pairs Wikipedia sections with tabular data and various metadata. |
| Outcome: | The proposed dataset can generate fluent and high quality texts but struggle with coherence and factuality. |
CoDesc: A Large Code–Description Parallel Dataset (2021.findings-acl)
Copied to clipboard
Masum Hasan, Tanveer Muttaqueen, Abdullah Al Ishtiaq, Kazi Sajeed Mehrab, Md. Mahim Anjum Haque, Tahmid Hasan, Wasi Ahmad, Anindya Iqbal, Rifat Shahriyar
| Challenge: | Existing models for natural language and programming languages are lagging behind due to a lack of large datasets and benchmarks. |
| Approach: | They present a large parallel dataset of Java methods and natural language descriptions that is used to train deep neural models. |
| Outcome: | The proposed dataset improves code summarization and code search by 22% and opens up possibilities for pretrained language models for Java. |
Deep Cognitive Reasoning Network for Multi-hop Question Answering over Knowledge Graphs (2021.findings-acl)
Copied to clipboard
| Challenge: | Knowledge Graphs (KGs) store structured human knowledge with nodes and edges being entities and relations between them. |
| Approach: | They propose a deep cognitive reasoning network that uses two phases to find answers in large candidate entity sets. |
| Outcome: | The proposed method significantly outperforms state-of-the-art methods on benchmark datasets. |
GoG: Relation-aware Graph-over-Graph Network for Visual Dialog (2021.findings-acl)
Copied to clipboard
| Challenge: | Experimental results show that our model outperforms the strong baseline in both generative and discriminative settings by a significant margin. |
| Approach: | They propose a relation-aware graph-over-graph network (GoG) for visual dialog . their model outperforms the strong baseline in both generative and discriminative settings . |
| Outcome: | The proposed model outperforms baseline models in both generative and discriminative settings by a significant margin. |
Joint Optimization of Tokenization and Downstream Model (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have reported that an appropriate tokenization depends on each downstream task. |
| Approach: | They propose a method to find an appropriate tokenization to a downstream task by optimizing a tokenizer and a model. |
| Outcome: | The proposed method improves on text classification and machine translation tasks. |
How does Attention Affect the Model? (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on the effectiveness of attention in NLP do not consider changes in semantic capability of different components. |
| Approach: | They propose a framework that exploits a convex hull representation of sequence semantics in an n-dimensional Semantic Euclidean Space and defines indicators to capture the impact of attention on sequence semantic. |
| Outcome: | The proposed framework exploits a convex hull representation of sequence semantics in an n-dimensional Semantic Euclidean Space and defines indicators to capture the impact of attention on sequence semantic. |
Contrastive Attention for Automatic Chest X-ray Report Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent studies show that learning-based models fail to accurately capture and describe abnormal regions due to data bias. |
| Approach: | They propose a model that compares the current input image with normal images to capture abnormal regions by contrasting the input image and normal images. |
| Outcome: | The proposed model can be easily incorporated into existing models to boost their performance under most metrics. |
O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for video captioning consider a sequence of frames and biases towards focused objects. |
| Approach: | They propose an Object-Oriented Non-Autoregressive approach to video captioning . it performs three steps: 1) identify the focused objects and predict their locations . 2) generate related attribute words and relation words of these focused objects to form a draft caption . |
| Outcome: | The proposed method achieves competitive results with the state-of-the-art methods but with higher diversity and faster inference speed. |
Better Chinese Sentence Segmentation with Reinforcement Learning (2021.findings-acl)
Copied to clipboard
| Challenge: | Chinese-English machine translation systems use ambiguous sentence boundaries, but English and Chinese use different orthographic conventions to designate sentence boundaries. |
| Approach: | They propose a segmentation policy that splits Chinese texts into segments that can be independently translated to maximise translation quality. |
| Outcome: | The proposed method improves the baseline BLEU score on the Chinese-English news translation task by +0.3 BLUE overall and the score on input segments that contain more than 60 words by +3 BL EU. |
Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuning (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in transfer learning have brought significant improvements to many natural language processing tasks. |
| Approach: | They propose a method of fitting a GBDT head on the features computed during finetuning to increase performance without additional computation by the neural network. |
| Outcome: | The proposed method improves on several NLI datasets using a strong baseline model (RoBERTa-large) with MNLI pretraining. |
Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling (2021.findings-acl)
Copied to clipboard
| Challenge: | Standard sequence labeling systems fail when processing noisy user-generated text or consuming the output of an OCR process. |
| Approach: | They propose an empirical error generation approach that employs a sequence-to-sequence model trained to perform translation from error-free to erroneous text. |
| Outcome: | The proposed method outperforms baseline noise generation and error correction techniques on the erroneous sequence labeling data sets. |
Spatial Dependency Parsing for Semi-Structured Document Information Extraction (2021.findings-acl)
Copied to clipboard
| Challenge: | Information extraction (IE) for semistructured document images is often considered as a sequence tagging problem . however, such a setup cannot handle complex spatial relationships and is not suitable for highly structured information. |
| Approach: | They propose a spatial dependency parsing problem that models complex spatial relationships . they evaluate it on receipts, name cards, forms, and invoices and compare it to other methods . |
| Outcome: | The proposed parser achieves similar or better performance on various kinds of documents compared to baselines including BERT-based IOB taggger. |
Reader-Guided Passage Reranking for Open-Domain Question Answering (2021.findings-acl)
Copied to clipboard
| Challenge: | Current open-domain question answering systems follow a Retriever-Reader architecture . current systems do not use a reranker, which reranked passages based on top predictions of the reader . |
| Approach: | They propose a reader-guIDEd reranking method that reranked passages based on top predictions . they show that RIDER achieves 10 to 20 absolute gains in top-1 retrieval accuracy . |
| Outcome: | The proposed method achieves 10 to 20 gains in top-1 retrieval accuracy and 1 to 4 Exact Match gains without training. |
Entity-Aware Abstractive Multi-Document Summarization (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models for multidocument summarization do not focus on explicitly modeling the underlying semantic information across documents. |
| Approach: | They propose an entityaware model for abstractive multi-document summarization that augments the classical Transformer-based encoder-decoder framework with a heterogeneous graph consisting of text units and entities as nodes. |
| Outcome: | The proposed model can deal with saliency and redundancy issues explicitly and can be used with pre-trained language models, arriving at improved performance. |
LenAtten: An Effective Length Controlling Unit For Text Summarization (2021.findings-acl)
Copied to clipboard
| Challenge: | Fixed length summarization (FLS) requires generating summaries with a preset number of characters or words. |
| Approach: | They propose a length control unit called LenAtten to break this trade-off by generating a short and coherent summary with the target length. |
| Outcome: | The proposed model improves controllability and ROGUE scores and generalizes well. |
XeroAlign: Zero-shot cross-lingual transformer alignment (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing zero-shot approaches to improve multilingual NLP tasks require translation of task data to bridge the gap between the source and target language. |
| Approach: | They propose a method for task-specific alignment of cross-lingual pretrained transformers such as XeroAlign that uses translated task data to encourage the model to generate similar sentence embeddings for different languages. |
| Outcome: | The proposed method performs on par with state-of-the-art models on a cross-lingual adversarial paraphrasing task and its text classification accuracy exceeds that of XLM-R trained with labelled data. |
Using Word Embeddings to Analyze Teacher Evaluations: An Application to a Filipino Education Non-Profit Organization (2021.findings-acl)
Copied to clipboard
| Challenge: | Using natural language processing, we examine teacher evaluations to improve educational programs. |
| Approach: | They apply natural language processing techniques to a Filipino education non-profit to analyze teacher evaluations written by Teacher Fellows. |
| Outcome: | The proposed framework can be applied to teacher evaluations from a Filipino education non-profit. |
Relation Classification with Entity Type Restriction (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods regard all relations as candidate relations for the two entities, which leads to inappropriate relations being candidate relations. |
| Approach: | They propose a paradigm which exploits entity types to restrict candidate relations by mutual restrictions. |
| Outcome: | The proposed paradigm improves GCN and SpanBERT on a standard dataset by 6.9 and 4.4 F1 points. |
Link Prediction on N-ary Relational Facts: A Graph-based Approach (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing work on knowledge graphs (KGs) focused on binary relations, but higher-arity relations are ubiquitous in real-world KGs. |
| Approach: | They propose a graph-based approach to link prediction on knowledge graphs using n-ary relational facts and edge-biased fully-connected attention. |
| Outcome: | The proposed approach performs substantially better than current state-of-the-art across a variety of n-ary relational benchmarks. |
GLGE: A New General Language Generation Evaluation Benchmark (2021.findings-acl)
Copied to clipboard
Dayiheng Liu, Yu Yan, Yeyun Gong, Weizhen Qi, Hang Zhang, Jian Jiao, Weizhu Chen, Jie Fu, Linjun Shou, Ming Gong, Pengcheng Wang, Jiusheng Chen, Daxin Jiang, Jiancheng Lv, Ruofei Zhang, Winnie Wu, Ming Zhou, Nan Duan
| Challenge: | Multi-task benchmarks focus on a range of Natural Language Understanding (NLU) tasks without considering the Natural Language Generation (NLG) models. |
| Approach: | They propose a multi-task benchmark for evaluating the generalization capabilities of NLG models across eight language generation tasks. |
| Outcome: | The proposed benchmarks are based on GLUE and Su-perGLUE for English and several other languages. |
AMBERT: A Pre-trained Language Model with Multi-Grained Tokenization (2021.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models such as BERT have shown great power in natural language understanding . fine-grained tokenizations have advantages and disadvantages for learning of pre-tried models . |
| Approach: | They propose a pretrained language model based on both fine-grained and coarse-grain tokenizations . they propose to use both tokenization techniques to learn pre-trained models . |
| Outcome: | The proposed model outperforms BERT on benchmark datasets for Chinese and English . it can perform better with the same computational cost as BERT, the authors show . |
Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on implicit exploration of multimodal coreference but neglect the importance of locating the objects explicitly in the visual content, which is associated with textual entities. |
| Approach: | They propose a multimodal incremental transformer with visual grounding which aims to explicitly locate related objects in the image guided by textual entities. |
| Outcome: | The proposed model achieves comparable performance on the VisDial v0.9 and v1.0 datasets. |
Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent years have seen a rapid growth of interest in building task-oriented dialogue systems. |
| Approach: | They propose a retrieve-and-memorize framework to deal with unbalanced distribution of system actions in dialogue datasets. |
| Outcome: | The proposed framework achieves competitive performance among state-of-the-art models on a large-scale task-oriented dialogue dataset. |
Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains (2021.findings-acl)
Copied to clipboard
| Challenge: | Large pre-trained models suffer from domain shift and are not optimal for specific domains. |
| Approach: | They propose a general approach to developing small, fast and effective pretrained models for specific domains by adapting off-the-shelf general pretrained model and performing task-agnostic knowledge distillation in target domains. |
| Outcome: | The proposed approach achieves better performance over the BERT BASE model in domain-specific tasks while 3.3 smaller and 5.1 faster than the BRT BASE. |
Decoupling Adversarial Training for Fair NLP (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing work assumes main task labels and protected attributes are available in the dataset, but protected labels are often unavailable or only available in limited numbers. |
| Approach: | They propose a method which uses only a small volume of protected labels to train adversarial models using a dataset with a discriminator. |
| Outcome: | The proposed method can be used to transfer private-labelled instances from one dataset to another without requiring large amounts of protected labels. |
GO FIGURE: A Meta Evaluation of Factuality in Summarization (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in text generation systems produce fluent, coherent, relevant, and factually correct text. |
| Approach: | They propose a metaevaluation framework for evaluating factuality evaluation metrics . they propose five necessary conditions to evaluate factual metrics on diagnostic factuity data . |
| Outcome: | The proposed framework provides robust evaluation that is extensible to multiple types of factual consistency and standard generation metrics, including QA metrics. |
DNN-driven Gradual Machine Learning for Aspect-term Sentiment Analysis (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for Aspect-Term Sentiment Analysis (ATSA) use pre-specified lexicons to extract sentiment features. |
| Approach: | They propose a Deep Neural Network-driven approach for Aspect-Term Sentiment Analysis (ATSA) that leverages shared features between labeled and unlabeled instances for knowledge conveyance. |
| Outcome: | The proposed approach consistently achieves state-of-the-art performance on real benchmark data. |
Error Detection in Large-Scale Natural Language Understanding Systems Using Transformer Models (2021.findings-acl)
Copied to clipboard
| Challenge: | Large-scale conversational assistants process every utterance using multiple models for domain, intent and named entity recognition. |
| Approach: | They combine utterance encodings from a RoBERTa model with the Nbest hypothesis produced by the production system to detect domain classification errors. |
| Outcome: | The proposed approach outperforms bi-LSTM models and a standalone model by 2.2% to 32.2% by ensembling multiple models. |
OutFlip: Generating Examples for Unknown Intent Detection with Natural Language Attack (2021.findings-acl)
Copied to clipboard
| Challenge: | Out-of-domain (OOD) input detection is vital in task-oriented dialogue systems . accepted OOD inputs lead to incorrect response of the system . |
| Approach: | They propose a method to generate out-of-domain samples from in-domain training datasets using OutFlip. |
| Outcome: | The proposed method significantly improves an intent classification model's out-of-domain detection performance. |
GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to solve geometric problems are dependent on handcraft rules and limited on small-scale datasets. |
| Approach: | They propose a Geometric Question Answering dataset with 5,010 geometric problems with corresponding annotated programs to illustrate the solving process. |
| Outcome: | The proposed method is significantly lower than human performance on the proposed dataset than on a publicly available dataset. |
SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extraction (2021.findings-acl)
Copied to clipboard
| Challenge: | Document-level relation extraction (doc-level RE) is a classification problem that predicts relations for all entity pairs in a document. |
| Approach: | They propose a document-level relation extraction architecture to represent intra- and inter-sentential relations in different ways. |
| Outcome: | The proposed architecture outperforms the state-of-the-art methods on the public datasets. |
KGPool: Dynamic Knowledge Graph Context Selection for Relation Extraction (2021.findings-acl)
Copied to clipboard
Abhishek Nadgeri, Anson Bastos, Kuldeep Singh, Isaiah Onando Mulang’, Johannes Hoffart, Saeedeh Shekarpour, Vijay Saraswat
| Challenge: | Existing methods for relation extraction (RE) use only expanded facts from the knowledge graph . |
| Approach: | They propose a method for relation extraction from a single sentence . they use a neural network to expand the context with additional facts from the KG . |
| Outcome: | The proposed method is more accurate than state-of-the-art methods on standard datasets. |
Better Combine Them Together! Integrating Syntactic Constituency and Dependency Representations for Semantic Role Labeling (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies use only one singleton syntax for semantic role labeling (SRL). |
| Approach: | They propose a TreeLSTM-based integration that integrates phrasal boundaries and semantic relations from dependency into a labelaware GCN solution for simultaneously modeling syntactic edges and labels. |
| Outcome: | The proposed system achieves state-of-the-art performance on span-based and dependency-based SRL. |
Keep the Primary, Rewrite the Secondary: A Two-Stage Approach for Paraphrase Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to generate paraphrases are decomposable, but some use a sequence-to-sequence model to generate each word in a uniform way. |
| Approach: | They propose a framework for identification then aggregation of input tokens and a custom decoder to generate paraphrases. |
| Outcome: | The proposed framework outperforms previous studies on two benchmark datasets and generates paraphrases in interpretable and controllable way. |
Contrastive Fine-tuning Improves Robustness for Neural Rankers (2021.findings-acl)
Copied to clipboard
| Challenge: | Current state-of-the-art neural rankers can deteriorate when exposed to noisy inputs or applied to a new domain. |
| Approach: | They propose a contrastive loss and ranking loss method for fine-tuning rankers that combine ranking loss and rank loss to improve their robustness to query reformulations and noise perturbations. |
| Outcome: | The proposed method outperforms data augmentation for robustifying rankers on four passage ranking datasets. |
Cross-Lingual Transfer in Zero-Shot Cross-Language Entity Linking (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing work on cross-language entity linking grounds mentions written in multiple languages to a monolingual knowledge base is lacking. |
| Approach: | They propose a task that uses multilingual BERT representations of both the mention and context as input and explore zero-shot language transfer. |
| Outcome: | The proposed model performs well in both monolingual and multilingual settings. |
TellMeWhy: A Dataset for Answering Why-Questions in Narratives (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models do not have the ability to answer "why" questions that require commonsense knowledge external to the narrative. |
| Approach: | They propose a crowd-sourced dataset that asks why characters perform actions . they show that state-of-the-art models are far below human performance on answering such questions . |
| Outcome: | The proposed dataset shows that state-of-the-art models are far below human performance on answering such questions. |
Dialogue in the Wild: Learning from a Deployed Role-Playing Game with Humans and Bots (2021.findings-acl)
Copied to clipboard
| Challenge: | prevailing paradigm in natural language processing research is to build a fixed dataset and freeze it, without any ability for the model to interact with humans using language at training time at all. |
| Approach: | They build and deploy a role-playing game where players converse with learning agents situated in an open-domain fantasy world. |
| Outcome: | The proposed game enables human players to learn from human conversations and improves on their models. |
Deep Learning against COVID-19: Respiratory Insufficiency Detection in Brazilian Portuguese Speech (2021.findings-acl)
Copied to clipboard
Edresson Casanova, Lucas Gris, Augusto Camargo, Daniel da Silva, Murilo Gazzola, Ester Sabino, Anna Levin, Arnaldo Candido Jr, Sandra Aluisio, Marcelo Finger
| Challenge: | Respiratory insufficiency is a symptom that requires hospitalization . a dataset was created to analyze COVID-19 patients and a control group . |
| Approach: | They used a dataset to build a Convolution Neural Network to detect respiratory insufficiency using MFCC representations. |
| Outcome: | The proposed method achieves 91.66% accuracy under real-life environmental conditions. |
Benchmarking Robustness of Machine Reading Comprehension Models (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks only evaluate models' robustness under test-time perturbations or adversarial attacks. |
| Approach: | They propose a model-agnostic benchmark to evaluate models' robustness under adversarial attacks. |
| Outcome: | The proposed model-agnostic benchmark evaluates models under four different types of adversarial attacks. |
Improving BERT with Syntax-aware Local Attention (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent studies show that attention-based models benefit from more focused attention over local regions. |
| Approach: | They propose a syntax-aware local attention which restrains attention over syntactically relevant words. |
| Outcome: | The proposed model performs better on all benchmark datasets, including sentence classification and sequence labeling tasks. |
A Dialogue-based Information Extraction System for Medical Insurance Assessment (2021.findings-acl)
Copied to clipboard
Shuang Peng, Mengdi Zhou, Minghui Yang, Haitao Mi, Shaosheng Cao, Zujie Wen, Teng Xu, Hongbin Wang, Lei Liu
| Challenge: | a new system that integrates advanced NLP technologies for medical insurance assessment is proposed . the average time cost of the procedure is reduced from 55 minutes to 35 minutes . |
| Approach: | They propose a dialogue-based information extraction system that integrates advanced NLP technologies for medical insurance assessment. |
| Outcome: | The proposed system reduces the time cost of the procedure from 55 minutes to 35 minutes and saves 30% human resources cost compared with the previous offline procedure. |
Prediction or Comparison: Toward Interpretable Qualitative Reasoning (2021.findings-acl)
Copied to clipboard
| Challenge: | Qualitative relationships are a significant portion of textual knowledge . current approaches use semantic parsers to transform natural language inputs into logical expressions or a "black-box" model to solve them in one step. |
| Approach: | They propose to use neural network modules to simulate qualitative reasoning tasks . they use two qualitative reasoning question answering datasets to test their methods . |
| Outcome: | Experiments on two qualitative reasoning question answering datasets show the proposed methods are general and general and interpretable. |
Boundary Detection with BERT for Span-level Emotion Cause Analysis (2021.findings-acl)
Copied to clipboard
| Challenge: | Emotion cause analysis (ECA) is an emerging topic in natural language processing, which aims to identify the reasons behind a given emotion. |
| Approach: | They propose to detect the precise boundaries of text spans conveying accurate emotion causes from the given context by a sequence labeling and position identification problem. |
| Outcome: | The proposed methods outperform existing models on two benchmark datasets on the emotion cause analysis task. |
On Commonsense Cues in BERT for Solving Commonsense Tasks (2021.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models can capture syntactic features, semantic information and factual knowledge, but structured commonsense knowledge is not captured well. |
| Approach: | They quantitatively investigate the presence of structural commonsense cues in BERT when solving commonsensense tasks and the importance of such cue for the model prediction. |
| Outcome: | The presence of commonsense knowledge is positively correlated to the model accuracy. |
Weakly Supervised Pre-Training for Multi-Hop Retriever (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for weakly supervised multi-hop pretraining require costly human annotation. |
| Approach: | They propose a method for weakly supervised multi-hop retriever pretraining without human efforts by generating vector representations of complex questions and subquestion as weak supervision for pre-training. |
| Outcome: | The proposed method is effective and robust on limited data and computational resources. |
Meet The Truth: Leverage Objective Facts and Subjective Views for Interpretable Rumor Detection (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing rumor detection methods provide detection labels while ignoring their explanation. |
| Approach: | a novel model is proposed to automatically classify rumors using Wikipedia documents . the model combines objective facts and subjective views to verify rumours . |
| Outcome: | a new model outperforms existing models on real-world Twitter datasets . the proposed model combines objective facts and subjective views to verify rumor . |
Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking (2021.findings-acl)
Copied to clipboard
| Challenge: | Chinese Spell Checking (CSC) aims to detect and correct erroneous characters for usergenerated text in Chinese. |
| Approach: | They propose a Chinese spell checker that leverages multimodal Chinese characters' information to predict the correct output. |
| Outcome: | The proposed model outperforms strong baselines on the SIGHAN benchmarks by a large margin. |
TransSum: Translating Aspect and Sentiment Embeddings for Self-Supervised Opinion Summarization (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on unsupervised opinion summarization and treat it as a normal multi-document summarizing task. |
| Approach: | They propose a selfsupervised opinion summarization framework TransSum that learns crucial aspect and sentiment embeddings of reviews using intra- and inter-group invariances. |
| Outcome: | The proposed framework outperforms baselines in generating informative, relevant and low-redundant summaries on three domains. |
Hashing based Efficient Inference for Image-Text Matching (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent work on image-text matching has focused on exploring interactions between images and sentences to improve performance without considering inference efficiency. |
| Approach: | They propose a hashing-based efficient inference module which can be plugged into existing frameworks to speed up inference step without reducing retrieval performance. |
| Outcome: | The proposed module can be plugged into existing framework to speed up inference step without reducing retrieval performance. |
Can the Transformer Learn Nested Recursion with Symbol Masking? (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on self-attention models show they can generalise to context-free languages . |
| Approach: | They use encoder-only models to train to generalise nested symbols . they find that the predictions made correspond to a simple parenthesis counting strategy . |
| Outcome: | The proposed model can generalise to nested structures at higher nesting depth and with a push-down automaton. |
Rationalization through Concepts (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models that explain complex decisions are limited because of their lack of interpretability. |
| Approach: | They propose a model that extracts text snippets as concepts and infers which ones are described in the document. |
| Outcome: | The proposed model outperforms state-of-the-art methods trained on each aspect label independently. |
Parallel Attention Network with Sequence Matching for Video Grounding (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to video grounding are sensitive to quality of proposals and inefficient because all proposal-query pairs are compared. |
| Approach: | They propose a Parallel Attention Network with Sequence matching to capture selfmodal contexts and cross-modal attentive information between video and text. |
| Outcome: | The proposed approach is superior to state-of-the-art methods on three datasets. |
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training (2021.findings-acl)
Copied to clipboard
| Challenge: | Symbolic music understanding is useful for many music applications, but lack of training data hinders representation learning. |
| Approach: | They propose a pre-trained model for music understanding that uses symbolic music data to train music representations. |
| Outcome: | The proposed model improves on four music understanding tasks. |
Evaluating the Efficacy of Summarization Evaluation across Languages (2021.findings-acl)
Copied to clipboard
| Challenge: | Using multilingual summarization evaluation methods is more reliable and interpretable than manual methods. |
| Approach: | They propose to use multilingual BERT within BERTScore to evaluate summarization evaluation metrics . they use English datasets that are not representative of modern summarizing systems . |
| Outcome: | The proposed methods perform well across all languages, at a level above that for English. |
CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for empathetic response generation ignore hierarchical relationships between different factors, leading to a weak ability of empathy modeling. |
| Approach: | They propose a multi-factor hierarchical framework for empathetic response generation which models the above three key factors in a hierarchically structured way. |
| Outcome: | The proposed model generates more empathetic responses than previous methods. |
UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Prediction (2021.findings-acl)
Copied to clipboard
| Challenge: | Mainstream methods that ignore the diversity among keyphrases or weakly capture the relation between tasks implicitly ignore keyphrase diversity. |
| Approach: | They propose a novel end-to-end learning framework that jointly learns to extract and generate keyphrases by exploiting latent semantic relation between extraction and generation. |
| Outcome: | The proposed approach outperforms mainstream methods on a benchmarked document on keyphrase prediction. |
As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing pre-trained language models are limited in their ability to train for English, which is a problem for many other languages. |
| Approach: | They propose to adapt existing generative language models to new languages by retraining lexical embeddings without tuning the Transformer layers. |
| Outcome: | The proposed method achieves lexical embeddings for Italian and Dutch that are aligned with the original English lexicals. |
Can Cognate Prediction Be Modelled as a Low-Resource Machine Translation Task? (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing work on cognate prediction based on similarities of two languages has not studied their differences or optimized architectural choices. |
| Approach: | They compare statistical and neural MT architectures to a bilingual setup to test their hypothesis . they use monolingual pretraining, backtranslation and multilinguality to test the hypothesis based on the results . |
| Outcome: | The proposed architectures can be used to generate cognates in a given language . the proposed architecture can be employed with monolingual pretraining, backtranslation and multilinguality . |
What if This Modified That? Syntactic Interventions with Counterfactual Embeddings (2021.findings-acl)
Copied to clipboard
| Challenge: | Prior art aims to uncover meaningful properties within model representations, but it is unclear how faithfully such probes portray information that the models actually use. |
| Approach: | They propose a technique for generating counterfactual embeddings within models . they produce evidence that some models use a tree-distancelike representation of syntax . |
| Outcome: | The proposed technique produces evidence that some models use tree-distancelike representations of syntax in downstream prediction tasks. |
Investigating Text Simplification Evaluation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies show that parallel TS corpora contain inaccurate simplifications and incorrect alignments. |
| Approach: | They propose to improve the distribution of parallel text simplification corpora to build more robust TS models. |
| Outcome: | The proposed models can be improved by improving the distribution of TS datasets. |
COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in pretrained language models have shown promising results on commonsense reasoning benchmark datasets. |
| Approach: | They propose a commonsense reasoning benchmark dataset with 4k sentence pairs . they propose 'gamified' model-in-the-loop setup to incentivize challenging samples . |
| Outcome: | The proposed benchmarks show that the proposed model achieves 71% standard accuracy and 51% pairwise accuracy, well below human performance. |
Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to combat online hatred using informed textual responses - called counter narratives - produce generic/repetitive responses and lack grounded and up-to-date evidence such as facts, statistics, or examples. |
| Approach: | They propose to automatically generate counter narratives using an external knowledge repository to provide more informative content to fight online hatred. |
| Outcome: | The proposed pipeline can generate suitable and informative counter narratives in in-domain and cross-domain settings. |
SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification (2021.findings-acl)
Copied to clipboard
| Challenge: | toxicity, hate speech, cyberbullying, and cyber-aggression are common themes in social media . authors present a dataset that is limited in size and biased towards offensive language . |
| Approach: | They present an expanded dataset that uses a taxonomy for offensive language identification . they show that using SOLID and OLID yields sizable performance gains . |
| Outcome: | The proposed dataset shows that it performs better than the OLID dataset for two different models. |
RealFormer: Transformer Likes Residual Attention (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing techniques to create Residual Attention Layer Transformer networks outperform the canonical Transformer on a wide spectrum of tasks. |
| Approach: | They propose a technique to create Residual Attention Layer Transformer networks that outperform the canonical Transformer on a wide spectrum of tasks. |
| Outcome: | The proposed technique outperforms the canonical Transformer on a wide spectrum of tasks including Masked Language Modeling, GLUE, SQUAD, Neural Machine Translation, WikiHop, HotpotQA, Natural Questions, and OpenKP. |
Promoting Graph Awareness in Linearized Graph-to-Text Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent applications of pretrained transformers to linearizations of graph inputs yield stateof-the-art results on graph-to-text tasks. |
| Approach: | They propose to use pretrained transformers to encode local graph structures . they find they can improve the quality of models' implicit graph encodings . |
| Outcome: | The proposed models can encode local graph structures and reconstruct corrupted inputs. |
Predicting cross-linguistic adjective order with information gain (2021.findings-acl)
Copied to clipboard
| Challenge: | Languages that allow multiple sequential adjective modifiers tend to exhibit strong intralanguage tendencies on the relative order of adjectives. |
| Approach: | They propose a quantitative account of adjective order across typologically-distinct languages based on maximizing information gain. |
| Outcome: | The proposed model addresses the left-right asymmetry of French-type ANA sequences without appeal to other mechanisms. |
A Survey of Data Augmentation Approaches for NLP (2021.findings-acl)
Copied to clipboard
Steven Y. Feng, Varun Gangal, Jason Wei, Sarath Chandar, Soroush Vosoughi, Teruko Mitamura, Eduard Hovy
| Challenge: | Data augmentation is a field of research that has been underexplored due to the discrete nature of language data. |
| Approach: | They present a comprehensive survey of data augmentation for NLP by summarizing the literature in a structured manner. |
| Outcome: | The proposed methods are used for popular NLP applications and tasks and highlight current challenges and directions for future research. |
Why Machine Reading Comprehension Models Learn Shortcuts? (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies show that many MRC models learn shortcuts to outwit benchmarks, but the performance is unsatisfactory in real-world applications. |
| Approach: | They propose to use shortcut questions to analyze learning difficulty of MRC models . they propose to analyze the learning difficulty regarding shortcut and challenging questions . |
| Outcome: | The proposed methods show that a large proportion of shortcut questions in training data make models rely on shortcut tricks excessively. |
Handling Cross- and Out-of-Domain Samples in Thai Word Segmentation (2021.findings-acl)
Copied to clipboard
Peerat Limkonchotiwat, Wannaphong Phatthiyaphaibun, Raheem Sarwar, Ekapol Chuangsuwanich, Sarana Nutanong
| Challenge: | Word segmentation is domain-dependent, which can be a challenge in low-resource languages like Thai and Urdu . a framework to handle out-of-domain inputs is proposed to improve word segmentation . |
| Approach: | They propose a domaingeneric domain adaptation framework and data augmentation technique to combat low-resource problems. |
| Outcome: | The proposed model outperforms the state-of-the-art Thai word segmentation method in out-of domain scenarios. |
Sensei: Self-Supervised Sensor Name Segmentation (2021.findings-acl)
Copied to clipboard
| Challenge: | Sensor names are alphanumeric strings that encode key contextual information such as their function or physical location. |
| Approach: | They propose a self-supervised framework that can learn to segment sensor names without human annotation. |
| Outcome: | The proposed framework can learn to segment sensor names without human annotation on buildings. |
Frustratingly Simple Few-Shot Slot Tagging (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing fewshot methods for slot tagging are weak in encoding slot name semantics and slot dependencies. |
| Approach: | They propose a simple and effective few-shot model for slot tagging which incorporates machine reading comprehension (MRC) using source domain and target domain data. |
| Outcome: | The proposed model outperforms state-of-the-art methods on the SNIPS dataset. |
Medical Code Assignment with Gated Convolution and Note-Code Interaction (2021.findings-acl)
Copied to clipboard
| Challenge: | Medical code assignment from clinical text is a longstanding challenge due to lengthy semantic information in medical notes. |
| Approach: | They propose a method to capture the semantic information of medical notes and a note-code interaction to automate medical code assignment from clinical text. |
| Outcome: | The proposed method outperforms state-of-the-art models on real-world clinical datasets and is on par with light-weighted baselines. |
Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches suffer from low confidence when retrieving evidence facts to fill the knowledge gap and lack transparent reasoning process. |
| Approach: | They propose a framework to exploit more valid facts while obtaining explainability for multi-hop question answering at web scale by dynamically constructing a semantic graph and reasoning over it. |
| Outcome: | The proposed framework surpasses existing approaches while maintaining high explainability on OpenBookQA and ARC-Challenge. |
Addressing Inquiries about History: An Efficient and Practical Framework for Evaluating Open-domain Chatbot Consistency (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to evaluate consistency capacity of open-domain chatbots are costly and low-efficient. |
| Approach: | They propose an efficient framework for evaluating consistency of open-domain chatbots . they use human judges to interact with chatbot, which is costly and low-efficient . |
| Outcome: | The proposed framework can assess the consistency capacity of chatbots and achieve a high ranking correlation with the human evaluation. |
Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Using connectionist temporal classification (CTC) for speech-to-text translation is counter-intuitive due to its monotonicity assumption. |
| Approach: | They propose to build a non-autoregressive speech-to-text translation model using connectionist temporal classification (CTC) their work shows transformer encoders can change the word order and points out the future research direction that needs to be explored more on non-Autoregressives speech translation. |
| Outcome: | The proposed model improves translation performance by using transformer encoders. |
Code Summarization with Structure-induced Transformer (2021.findings-acl)
Copied to clipboard
| Challenge: | Code summarization (CS) is a promising area in recent language understanding . previous work using structurebased traversal or non-sequential models to learn structural program semantics has shown no performance gain . |
| Approach: | They propose to use a structure-based traversal model to learn structural program semantics to generate human language automatically for programming language in the format of source code. |
| Outcome: | Experiments show that the proposed method achieves state-of-the-art on benchmarks. |
Scheduled Dialog Policy Learning: An Automatic Curriculum Learning Framework for Task-oriented Dialog System (2021.findings-acl)
Copied to clipboard
| Challenge: | et al., 2013) show that dialog policy learning is an important component of the task-oriented dialogue system. |
| Approach: | They propose a framework that integrates curriculum learning and policy optimization . they propose to train dialog agents from easy dialogues to complex ones . |
| Outcome: | The proposed framework outperforms the state-of-the-art model on multi-task dialogues. |
Do Explanations Help Users Detect Errors in Open-Domain QA? An Evaluation of Spoken vs. Visual Explanations (2021.findings-acl)
Copied to clipboard
| Challenge: | despite interest in explainable AI, there is increasing skepticism as to whether explanations are useful to end-users in downstream applications. |
| Approach: | They conduct user studies to measure whether explanations help users decide when to accept or reject an ODQA system's answer. |
| Outcome: | The proposed study shows that explanations outperform baselines across modalities but the best strategy varies with the modality. |
OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for aligning knowledge graph entities ignore the ontology which contains critical meta information such as classes and membership relationships with entities. |
| Approach: | They propose an ontology-guided method where KGs and ontologies are jointly embedded. |
| Outcome: | Extensive experiments on seven public and industrial benchmarks show the ontology-guided method performs well and is cost-effective. |
Learning Algebraic Recombination for Compositional Generalization (2021.findings-acl)
Copied to clipboard
Chenyao Liu, Shengnan An, Zeqi Lin, Qian Liu, Bei Chen, Jian-Guang Lou, Lijie Wen, Nanning Zheng, Dongmei Zhang
| Challenge: | Neural sequence models exhibit limited compositional generalization ability in semantic parsing tasks. |
| Approach: | They propose an end-to-end neural model to learn algebraic recombination for compositional generalization. |
| Outcome: | The proposed model is based on two realistic and comprehensive compositional generalization benchmarks. |
Out of Order: How important is the sequential order of words in a sentence in Natural Language Understanding tasks? (2021.findings-acl)
Copied to clipboard
| Challenge: | In July 2019, RoBERTa was the first to surpass a human baseline on GLUE . since then, 13 more methods have outperformed humans on the GLu leaderboard . |
| Approach: | They found that 75% to 90% of correct predictions of BERT-based classifiers remain constant after input words are randomly shuffled. |
| Outcome: | The proposed model outperforms humans on GLUE and SQuAD 2.0. |
RevCore: Review-Augmented Conversational Recommendation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing conversational recommendation systems lack item information when conducted on short dialogue history and unfamiliar items. |
| Approach: | They propose a framework where reviews are seamlessly incorporated into conversational recommendation systems. |
| Outcome: | The proposed framework yields better performance on recommendation and conversation responding. |
Awakening Latent Grounding from Pretrained Language Models for Semantic Parsing (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent years pretrained language models (PLMs) have shown their power on modeling language . however, few efforts have been made to explore grounding capabilities of PLMs . |
| Approach: | They propose to use pretrained language models to explore syntactic structures . they propose to combine their approach with an erasingthen-awakening approach . their results show that the approach can awaken latent grounding, which is understandable to humans . |
| Outcome: | Empirical studies show that the proposed approach can awaken latent grounding . it shows great potential to benefit downstream semantic parsing models, it says . |
Enhancing Label Correlation Feedback in Multi-Label Text Classification via Multi-Task Learning (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to multi-task learning fail to capture label correlations . Existing methods suffer from label order dependency, label combination over-fitting and error propagation problems. |
| Approach: | They propose a novel approach with multi-task learning to enhance label correlation feedback. |
| Outcome: | The proposed method outperforms baselines on AAPD and RCV1-V2 datasets. |
Fusing Context Into Knowledge Graph for Commonsense Question Answering (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to combine language modeling and knowledge graphs (KG) lack the context to provide a more precise understanding of the concepts. |
| Approach: | They propose to use external entity descriptions to provide contextual information for commonsense question answering models. |
| Outcome: | The proposed model achieves state-of-the-art among non-generative models in OpenBookQA and is the first of its kind in the field. |
Unsupervised Energy-based Adversarial Domain Adaptation for Cross-domain Text Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Extensive experiments on multidomain sentiment classification and yes/no question-answering classification are conducted. |
| Approach: | They propose an unsupervised energy-based adversarial domain adaptation framework that maps the text sequences from both source and target domains to a feature space. |
| Outcome: | The proposed framework improves on multidomain sentiment classification and Yes/No question-answering classification. |
Survival text regression for time-to-event prediction in conversations (2021.findings-acl)
Copied to clipboard
| Challenge: | a recent study has modelled time-to-event prediction tasks as classification tasks . authors: this is contrived and less informative than traditional classification models . |
| Approach: | They propose to frame time-to-event prediction tasks as classification tasks . they use survival regression techniques commonly used in healthcare and reliability engineering . |
| Outcome: | The proposed models outperform text regression methods and comparable classification models on three datasets. |
Unsupervised Knowledge Selection for Dialogue Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge selection tasks require the preidentified knowledge to generate informative dialogues. |
| Approach: | They propose a novel method to supervise knowledge selection when the gold knowledge label is unknown by obtaining an oracle knowledge label via distant supervision and leverage knowledge distillation to alleviate the noisy labeling problem of distant supervision. |
| Outcome: | The proposed method outperforms strong supervised baselines on two knowledge-grounded dialogue datasets and generates more informative responses. |
Minimax and Neyman–Pearson Meta-Learning for Outlier Languages (2021.findings-acl)
Copied to clipboard
| Challenge: | Model-agnostic meta-learning (MAML) is a strategy to learn resource-poor languages in a sample-efficient fashion. |
| Approach: | They propose a model-agnostic meta-learning strategy that minimizes the expected risk across languages with a uniform prior . they propose 'minimax' and 'neyman-pearson' models that constrain the risk in each language to a maximum threshold. |
| Outcome: | The proposed model reduces the maximum risk across languages while constraining the risk in each language to a maximum threshold. |
On-the-Fly Attention Modulation for Neural Generation (2021.findings-acl)
Copied to clipboard
Yue Dong, Chandra Bhagavatula, Ximing Lu, Jena D. Hwang, Antoine Bosselut, Jackie Chi Kit Cheung, Yejin Choi
| Challenge: | Degeneration of neural text is associated with insufficient learning of task-specific characteristics by the attention mechanism. |
| Approach: | They propose to use attention modulation to inject priors into inference to improve fluency, creativity, and commonsense reasoning in neural text generation models. |
| Outcome: | The proposed method improves fluency, creativity, and commonsense reasoning, and significantly reduces sentence-level repetition. |
Grammar-Constrained Neural Semantic Parsing with LR Parsers (2021.findings-acl)
Copied to clipboard
| Challenge: | a context-free grammar can be used to enforce syntactical constraints when predicting logical forms. |
| Approach: | They propose a model that uses an LR parser to maintain syntactically valid sequences throughout the decoding procedure. |
| Outcome: | The proposed model is conceptually simpler and adds less overhead during inference compared to other approaches . it is compared with existing grammar-guided decoding frameworks and is cost-effective . |
Enhanced Metaphor Detection via Incorporation of External Knowledge Based on Linguistic Theories (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for metaphor detection take little consideration on linguistic theories of metaphor detection. |
| Approach: | They propose two BERT-based models for metaphor detection based on examples and definitions of words from the Oxford Dictionary. |
| Outcome: | The proposed models achieve state-of-the-art performance on two established metaphor datasets and are highly interpretable. |
Controlling Text Edition by Changing Answers of Specific Questions (2021.findings-acl)
Copied to clipboard
| Challenge: | In many situations, we need to change specific content in a document. |
| Approach: | They propose a task where we take a long text, a question, and a target answer as input and output a minimally modified text so that it fits the target answer. |
| Outcome: | The proposed task is based on the existing dataset WIKIBIO and tests on a test set. |
Grammar-Based Patches Generation for Automated Program Repair (2021.findings-acl)
Copied to clipboard
| Challenge: | Automated program repair (APR) aims to find an automatic solution to program language bugs without human intervention. |
| Approach: | They propose a grammar-based rule-rule model which regards the repair process as the transformation of grammar rules and employs a tree-based self-attention approach to guarantee grammar correctness. |
| Outcome: | The proposed model outperforms the state-of-the-art models on a Java dataset in terms of generated code accuracy. |
Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction (2021.findings-acl)
Copied to clipboard
Tianyu Gao, Xu Han, Yuzhuo Bai, Keyue Qiu, Zhiyu Xie, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou
| Challenge: | Distantly supervised relation extraction (RE) has attracted much attention in the past few years . previous methods to evaluate models manually or directly on autolabeled data have produced inaccurate evaluations . |
| Approach: | They propose to use distant supervision to generate large-scale autolabeled data . they build manually-annotated test sets for two DS-RE datasets and evaluate models . |
| Outcome: | The proposed method produces 53% wrong labels at the entity pair level in the popular NYT10 dataset. |
GCRC: A New Challenging MRC Dataset from Gaokao Chinese for Explainable Evaluation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing machine reading comprehension datasets lack an explainable evaluation of systems' reasoning capabilities. |
| Approach: | They propose a dataset with multi-choice questions that evaluates MRC systems' reasoning process . they use sentence-level relevant supporting facts, error reason of distractors to evaluate MRC . |
| Outcome: | The proposed dataset is more challenging and useful for identifying limitations of existing MRC systems in an explainable way. |
Zero-shot Label-Aware Event Trigger and Argument Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing work on event extraction relies on labor-intensive annotation, ignoring semantic meaning of event types' labels. |
| Approach: | They propose a zero-shot event extraction approach that first identifies events with existing tools and then maps them to a given taxonomy of event types in a no-shot manner. |
| Outcome: | The proposed approach doubles the performance of previous approaches on a ACE-2005 dataset . it leverages label representations induced by pre-trained language models and maps events to the target types . |
Incorporating Global Information in Local Attention for Knowledge Representation Learning (2021.findings-acl)
Copied to clipboard
| Challenge: | Graph Attention Networks (GATs) are a promising model that takes advantage of localized attention mechanism to perform knowledge representation learning (KRL) on graph-structure data. |
| Approach: | They propose to incorporate global information into the GAT family of models by using an attention-based global random walk algorithm. |
| Outcome: | Experimental results on KG entity prediction against the state-of-the-arts demonstrate the effectiveness of the proposed model. |
Exploiting Position Bias for Robust Aspect Sentiment Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Aspect sentiment classification models suffer from the issue of robustness when domains of test and training data are different or test data is adversarially perturbed. |
| Approach: | They propose two mechanisms for capturing position bias to reduce the probability of mis-attending . they propose position-biased weight and position-based dropout to enhance existing models . |
| Outcome: | The proposed approaches improve the robustness and effectiveness of existing models. |
MRN: A Locally and Globally Mention-Based Reasoning Network for Document-Level Relation Extraction (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on document-level relation extraction focus on sentencelevel RE, but recent studies reveal that a large number of relations can actually be expressed through multiple sentences, which necessitates document- level RE. |
| Approach: | They propose a document-level relation extraction model that captures local and global contextual information as well as close and distant mention interactions. |
| Outcome: | The proposed model outperforms state-of-the-art models on three widely used datasets, namely DocRED, CDR, and GDA. |
Adversary-Aware Rumor Detection (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing rumor detection models do not detect malicious attacks, e.g., framing. |
| Approach: | They propose a weighted-edge transformer-graph network and position-aware Adversarial Response Generator to improve the vulnerability of detection models. |
| Outcome: | The proposed framework achieves state-of-the-art on various rumor detection tasks and maintains performance under adversarial learning. |
LICHEE: Improving Language Model Pre-training with Multi-grained Tokenization (2021.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models are trained based on single-grained tokenization, making it hard to learn the precise meaning of coarse-grain words and phrases. |
| Approach: | They propose a language model pretraining method that incorporates multi-grained information of input text into pre-trained language models. |
| Outcome: | The proposed method improves performance on CLUE and SuperGLUE in Chinese and English with little extra inference cost. |
Detecting Hallucinated Content in Conditional Neural Sequence Generation (2021.findings-acl)
Copied to clipboard
Chunting Zhou, Graham Neubig, Jiatao Gu, Mona Diab, Francisco Guzmán, Luke Zettlemoyer, Marjan Ghazvininejad
| Challenge: | Neural sequence models can generate fluent sentences, but they can also hallucinate additional content not supported by the input. |
| Approach: | They propose a task to predict whether each token in the output sequence is hallucinated and collect manually annotated evaluation sets for this task. |
| Outcome: | The proposed method outperforms baseline methods on machine translation and abstractive summarization datasets and achieves significant improvements in both supervised and unsupervised settings. |
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters (2021.findings-acl)
Copied to clipboard
Ruize Wang, Duyu Tang, Nan Duan, Zhongyu Wei, Xuanjing Huang, Jianshu Ji, Guihong Cao, Daxin Jiang, Ming Zhou
| Challenge: | Existing methods for injecting knowledge into pre-trained models are inconsistent and can flush out knowledge when multiple kinds of knowledge are injected. |
| Approach: | They propose a framework that retains the original parameters of pre-trained models fixed and supports the development of versatile knowledge-infused models. |
| Outcome: | The proposed framework retains the original parameters of the pre-trained model fixed and supports the development of versatile knowledge-infused models. |
Global Attention Decoder for Chinese Spelling Error Correction (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for Chinese spelling error correction focus on local contextual information, thus misleading the user and reducing performance. |
| Approach: | They propose a global attention decoder that learns the global relationship of correct input characters and candidates of potential error characters. |
| Outcome: | The proposed method outperforms all competitor models by a large margin of up to 6.2% on three human-annotated datasets. |
Jointly Identifying Rhetoric and Implicit Emotions via Multi-Task Learning (2021.findings-acl)
Copied to clipboard
| Challenge: | Experimental results validate the benefit of the proposed model over the state-of-the-art baselines for rhetoric and emotion identification tasks. |
| Approach: | They propose a multi-task learning framework that can encode categorical correlation between tasks to improve rhetoric and emotion identification problem. |
| Outcome: | The proposed model can encode the categorical correlation between tasks to improve rhetoric and emotion identification problem. |
Exploring the Role of Context in Utterance-level Emotion, Act and Intent Classification in Conversations: An Empirical Study (2021.findings-acl)
Copied to clipboard
| Challenge: | utterance-level dialogue understanding tasks are often performed at utterrance level and are often conjoined together under the umbrella of utterence-level dialog understanding. |
| Approach: | They propose to use a contextual utterance-level dialogue understanding baseline as a strong framework for six dialogue-understanding tasks. |
| Outcome: | The proposed framework can be easily adapted for other tasks for similar purposes. |
Encouraging Neural Machine Translation to Satisfy Terminology Constraints (2021.findings-acl)
Copied to clipboard
| Challenge: | a new approach to encourage neural machine translation to satisfy lexical constraints is proposed . a BLEU score and percentage of generated constraint terms are improved by the proposed method . |
| Approach: | They propose a method that encourages neural machine translation to satisfy lexical constraints at training step . they use a simplified augmentation strategy without source factors and constraint token masking to make it easier to learn the copy behavior . |
| Outcome: | The proposed method improves on baselines in terms of BLEU score and percentage of generated constraint terms. |
BertGCN: Transductive Text Classification by Combining GNN and BERT (2021.findings-acl)
Copied to clipboard
| Challenge: | Text classification is a core task in natural language processing (NLP) Graph neural networks (GNNs) serve as an effective approach for transductive learning. |
| Approach: | They propose a model that combines large scale pretraining and transductive learning for text classification. |
| Outcome: | The proposed model achieves SOTA performance on a wide range of datasets. |
Putting words into the system’s mouth: A targeted attack on neural machine translation using monolingual data poisoning (2021.findings-acl)
Copied to clipboard
Jun Wang, Chang Xu, Francisco Guzmán, Ahmed El-Kishky, Yuqing Tang, Benjamin Rubinstein, Trevor Cohn
| Challenge: | Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, they are also vulnerable to training attacks. |
| Approach: | They propose a poisoning attack in which a malicious adversary inserts a small poisoned sample of monolingual text into a training set of a system trained using back-translation. |
| Outcome: | The proposed attack is based on two methods that can be used to craft poisoned examples. |
Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to extract triplets from sentences neglect the mutual information between aspects and have the problem of error propagation. |
| Approach: | They propose a Semantic and Syntactic Enhanced aspect Sentiment triplet Extraction model to exploit the syntactical and semantic relationships between the triplet elements and jointly extract them. |
| Outcome: | The proposed model outperforms existing methods on four benchmark datasets and significantly outperformed existing approaches. |
UserAdapter: Few-Shot User Learning in Sentiment Analysis (2021.findings-acl)
Copied to clipboard
| Challenge: | Adapting a model to a handful of personalized data is challenging, authors say . standard fine-tuning requires hundreds of millions of parameters for each user . |
| Approach: | They propose a lightweight method that clamps millions of parameters of a Transformer model and optimizes a tiny user-specific vector. |
| Outcome: | The proposed method improves accuracy on Yelp and IMDB datasets and reduces the number of parameters added for each user. |
PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Support (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing research on text-based mental health counseling is limited due to the lack of relevant corpora in Chinese language. |
| Approach: | They propose a Chinese dataset of psychological health support in the form of question and answer pair that is crawled from a mental health service platform and contains 22K questions and 56K long and wellstructured answers. |
| Outcome: | The proposed dataset contains 22K questions and 56K long and wellstructured answers. |
RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledge (2021.findings-acl)
Copied to clipboard
| Challenge: | a riddle-style commonsense questions require complex commonsensense reasoning and figurative language skills . there is currently no dataset aimed at testing these abilities . authors propose a new multiple-choice question answering task . |
| Approach: | They propose a new multiple-choice question answering task that uses a large dataset for riddlestyle commonsense questions. |
| Outcome: | The proposed task comes with the first large dataset for answering riddlestyle commonsense questions. |
Learning to Generate Questions by Learning to Recover Answer-containing Sentences (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent research has focused on synthetically generating a question from a given context and an annotated answer by training an additional generative model. |
| Approach: | They propose a method that learns to generate contextually rich questions by recovering answer-containing sentences. |
| Outcome: | The proposed approach improves the quality and accuracy of existing models and achieves comparable results to the state-of-the-art on MS MARCO and NewsQA. |
Learning Slice-Aware Representations with Mixture of Attentions (2021.findings-acl)
Copied to clipboard
| Challenge: | Real-world machine learning systems are achieving excellent performance in terms of coarse-grained metrics like overall accuracy and F-1 score. |
| Approach: | They extend slice-based learning (SBL) with a mixture of attentions to learn slice-aware dual attentive representations. |
| Outcome: | The proposed approach outperforms the baseline method and the original SBL approach on monitored slices with two natural language understanding tasks. |
Making Better Use of Bilingual Information for Cross-Lingual AMR Parsing (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing work on meaning representations for English and other languages finds that concepts in their predicted AMR graphs are less specific. |
| Approach: | They propose a cross-lingual AMR parser that can predict more precise concepts by translating translated texts and non-English texts. |
| Outcome: | The proposed model surpasses state-of-the-art parser by 10.6 points on Smatch F1 score. |
Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation Approach (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent years, neural paraphrase generation models have demonstrated superior performance, but the output paraphrase still lacks diversity. |
| Approach: | They propose a back-translation guided multi-round paraphrase generation framework which leverages multi- round paraphrases to improve diversity while preserving semantic information. |
| Outcome: | The proposed model improves diversity while preserving semantic information. |
Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models for KG-to-text generation are based on pretrained language models. |
| Approach: | They propose to automatically generate a text that describes the facts in knowledge graph (KG) they leverage the excellent capacities of pretrained language models (PLMs) in language understanding and generation. |
| Outcome: | The proposed model outperforms all comparison methods on fully-supervised and fewshot settings. |
Better Robustness by More Coverage: Adversarial and Mixup Data Augmentation for Robust Finetuning (2021.findings-acl)
Copied to clipboard
| Challenge: | Pretrained language models perform poorly under adversarial attacks due to the large search space. |
| Approach: | They propose a method to cover a much larger proportion of the attack search space by adding textual adversarial examples during training. |
| Outcome: | The proposed method covers a much larger proportion of the attack search space. |
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer (2021.findings-acl)
Copied to clipboard
| Challenge: | Autoregressive text style transfer models often ignore part of the source sentence and generate some irrelevant words with strong styles. |
| Approach: | They propose a non-autoregressive generator for unsupervised text style transfer which explicitly models word alignments to suppress irrelevant words. |
| Outcome: | The proposed generator significantly improves performance and provides explainable word alignments. |
HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management (2021.findings-acl)
Copied to clipboard
| Challenge: | Task-oriented dialog systems typically manage structured knowledge to guide goal-oriented conversations. |
| Approach: | They propose a TOD system with hybrid knowledge management, HyKnow, which extends the belief state to manage both structured and unstructured knowledge. |
| Outcome: | The proposed model outperforms existing TOD systems in the evaluation of a multiWOZ dataset on unstructured knowledge with strong end-to-end performance. |
Target-oriented Fine-tuning for Zero-Resource Named Entity Recognition (2021.findings-acl)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is one of the fundamental tasks in natural language processing. |
| Approach: | They propose four practical guidelines to guide knowledge transfer and task finetuning . they propose a framework to exploit data from three aspects in a unified training manner . |
| Outcome: | The proposed framework improves on six benchmarks and shows that it is state-of-the-art in five languages. |
BERT-Defense: A Probabilistic Model Based on BERT to Combat Cognitively Inspired Orthographic Adversarial Attacks (2021.findings-acl)
Copied to clipboard
| Challenge: | adversarial attacks expose important blind spots of deep learning systems, authors show . word and sentence-level attacks tend to be more difficult to defend via spelling correction modules . character-level attack scenarios often involve finding semantic paraphrases of input . |
| Approach: | They propose a model that probabilistically combines context-independent word level information with context-dependent information from BERT's masked language modeling to combat low-level orthographic attacks. |
| Outcome: | The proposed model outperforms a spellchecker and Pruthi's model on a character-level benchmark. |
Event Detection as Graph Parsing (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to event detection focus on using syntactic dependency structures or external knowledge to boost the performance. |
| Approach: | They propose a graph parsing problem that explicitly models multiple event correlations and utilizes rich information conveyed by event type and subtype. |
| Outcome: | The proposed model outperforms existing models on the public ACE2005 dataset by 4.2% on the dataset. |
Toward Fully Exploiting Heterogeneous Corpus:A Decoupled Named Entity Recognition Model with Two-stage Training (2021.findings-acl)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is a fundamental and widely used task in natural language processing. |
| Approach: | They propose a decoupled NER model with two-stage training to take advantage of heterogeneous corpus, including dictionaries, distantly supervised instances, and human-annotated instances. |
| Outcome: | Empirical results show that the proposed model improves against baselines and can be scaled to a large extent. |
Discriminative Reasoning for Document-level Relation Extraction (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models use graph networks to implicitly model reasoning skills . but it is yet to be seen whether modeling these reasoning skills implicitly is competitive with intuitive reasoning skills between one entity pair in this document. |
| Approach: | They propose a discriminative reasoning framework to explicitly model the paths of reasoning skills between entity pairs in a document. |
| Outcome: | The proposed method outperforms the previous state-of-the-art on the large-scale DocRE dataset. |
Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches for few-shot text classification rely on exploitation of lexical features and distributional signatures on training data, while neglecting to strengthen the model's ability to adapt to new tasks. |
| Approach: | They propose a meta-learning framework integrated with an adversarial domain adaptation network to improve the model's adaptive ability and generate high-quality text embedding for new classes. |
| Outcome: | The proposed framework outperforms the state-of-the-art models on four datasets and shows clear superiority over existing models. |
Documents Representation via Generalized Coupled Tensor Chain with the Rotation Group constraint (2021.findings-acl)
Copied to clipboard
| Challenge: | despite the diversity of linguistic structures, vector embedding models lack order-preserving properties . current methods for learning linguistic structure can be expensive and time-consuming . |
| Approach: | They propose a method for embedding documents and words in rotation group . they capture word order and higher-order word interactions . |
| Outcome: | The proposed model achieves the best results in document classification benchmarks. |
Improving Unsupervised Extractive Summarization with Facet-Aware Modeling (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing extractive summarization methods tend to select sentences within the same facet, which leads to facet bias. |
| Approach: | They propose a facet-aware centrality-based ranking model that gives a weight to the sentence centrality score. |
| Outcome: | The proposed method outperforms baseline models on a wide range of summarization tasks and performs comparably to other models. |
Improving Gradient-based Adversarial Training for Text Classification by Contrastive Learning and Auto-Encoder (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent work has shown that models can be easily fooled by intentionally designed adversarial examples. |
| Approach: | They propose two efficient approaches for generating adversarial perturbations on embeddings and propose two new approaches to help model learn adversarials more efficiently. |
| Outcome: | The proposed approaches outperform strong baselines on various text classification datasets and the model's performance drops less under adversarial attack. |
Multi-Granularity Contrasting for Cross-Lingual Pre-Training (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to pre-training focus on embedding alignment, but they neglect the modeling of bidirectional contexts. |
| Approach: | They propose a framework to learn languageuniversal representations using multi-granularity contrasting framework . they encode semantic equivalents from different languages into similar representations . |
| Outcome: | The proposed framework can achieve significant performance gains in machine translation and cross-lingual language understanding. |
A Comparison between Pre-training and Large-scale Back-translation for Neural Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | BERT is a promising technique to improve NMT, but how it outperforms standard NMT is understudied. |
| Approach: | We compare MT engines trained with pre-trained BERT and back-translation with incrementally larger amounts of data. |
| Outcome: | The proposed technique outperforms standard NMT models on morphology and syntax. |
Bi-Granularity Contrastive Learning for Post-Training in Few-Shot Scene (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to fine-tune pre-trained models to downstream tasks are limited by labeled examples. |
| Approach: | They propose to apply post-training on unlabeled task data before fine-tuning by contrastive learning that considers either token-level or sequence-level similarity. |
| Outcome: | Empirical results show that contrastive masked language modeling surpasses other methods in few-shot settings without the need for data augmentation. |
Fusing Label Embedding into BERT: An Efficient Improvement for Text Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to improve text classification performance of pre-trained models have been used to improve their performance. |
| Approach: | They propose a method for improving BERT's performance by using a label embedding technique while keeping almost the same computational cost. |
| Outcome: | The proposed method improves BERT's performance on six text classification benchmark datasets while keeping almost the same computational cost. |
KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on partial aspects of knowledge abstraction, concretization, and completion (KACC). |
| Approach: | They propose a unified knowledge graph benchmark to improve existing benchmarks . they collect new datasets that contain larger concept graphs and cross-view links . |
| Outcome: | The proposed benchmark improves existing benchmarks in terms of dataset scale, task coverage, and difficulty. |
A Query-Driven Topic Model (2021.findings-acl)
Copied to clipboard
| Challenge: | Topic modeling is an unsupervised method for revealing the hidden semantic structure of a corpus. |
| Approach: | They propose a query-driven topic model that allows users to specify a simple query in words or phrases and return query-related topics. |
| Outcome: | The proposed model is particularly attractive when the query has a low occurrence in a text corpus, making it difficult for traditional topic models to identify relevant topics. |
How Reliable are Model Diagnostics? (2021.findings-acl)
Copied to clipboard
| Challenge: | Contemporary statistical models trade off interpretability and simplicity for powerful parameterizations and inductive biases, enabling impressive performance. |
| Approach: | They examine three recent models and find they are not yet reliable . they also formulate recommendations for practitioners and researchers . |
| Outcome: | The proposed models are not as reliable as previously assumed, the authors argue . their findings suggest that they are needed for improving models and training setups . |
Gaussian Process based Deep Dyna-Q approach for Dialogue Policy Learning (2021.findings-acl)
Copied to clipboard
| Challenge: | Reinforcement learning (RL) is the main dialogue policy learning method in recent years. |
| Approach: | They propose a Gaussian Process based Deep Dyna-Q approach to dialogue policy learning . they propose evaluating the quality of experiences generated by the world model using a discriminator . |
| Outcome: | The proposed approach improves the effectiveness and efficiency of dialogue policy learning by 20% with fewer human-machine interactions. |
CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understanding (2021.findings-acl)
Copied to clipboard
| Challenge: | Scientific document understanding is challenging due to the highly domain specific nature of scientific language. |
| Approach: | They propose a large, contextualized, rigorously cleaned labelled dataset for cite-worthiness detection built from extracted scientific documents. |
| Outcome: | The proposed model improves on a paragraphlevel contextualized sentence labelling model based on Longformer . the model shows a 5 F1 point improvement over SciBERT which considers only individual sentences . |
Cross-Lingual Cross-Domain Nested Named Entity Evaluation on English Web Texts (2021.findings-acl)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is a key task in Natural Language Processing, but most existing work on NER ignores the recognition of nested entities. |
| Approach: | They propose to annotate five web domains for nested named entities on top of the English Web Treebank (EWT) . they propose to use the English web treebank to perform cross-domain evaluations. |
| Outcome: | The proposed dataset covers five domains and includes transfer results from German and Danish. |
Counter-Argument Generation by Attacking Weak Premises (2021.findings-acl)
Copied to clipboard
| Challenge: | a recent work explores the generation of counter-arguments by undermining one of its premises . identifying the argument's weak premises is key to effective countering, we hypothesize . |
| Approach: | They propose a pipeline approach that first assesses the argument's weak premises and generates a counter-argument undermining the weakest among them. |
| Outcome: | The proposed approach undermins arguments by attacking weak premises . human annotators favor the proposed approach over state-of-the-art approaches . |
Alternated Training with Synthetic and Authentic Data for Neural Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to synthesizing data in NMT focus on leveraging monolingual data in training. |
| Approach: | They propose alternated training with synthetic and authentic data to improve NMT models' performance. |
| Outcome: | The proposed approach improves Chinese-English and German-English translation tasks over strong baselines. |
Template-Based Named Entity Recognition Using BART (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for fewshot NER do not make full use of knowledge transfer in NER model parameters. |
| Approach: | They propose a template-based method for NER that treats NER as a language model ranking problem in a sequence-to-sequence framework. |
| Outcome: | The proposed method achieves 92.55% F1 score on the CoNLL03 task and significantly better than fine-tuning BERT 10.88%, 15.34%, and 11.73% F1 scores on the MIT Movie, the ATIS, and the MATLAB task. |
“Does it Matter When I Think You Are Lying?” Improving Deception Detection by Integrating Interlocutor’s Judgements in Conversations (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for deception detection are based on interrogator's perceptions of truth-bias . despite its frequent occurrences, human is not good at detecting deceptions despite inclination of truth bias . |
| Approach: | They propose a Judgmental-Enhanced Automatic Deception Detection Network that explicitly considers interrogator's perceived truths-deceptions with three types of speechlanguage features extracted during a conversation. |
| Outcome: | The proposed method outperforms the current state-of-the-art approach without conditioning on interrogator's judgements. |
High-Quality Dialogue Diversification by Intermittent Short Extension Ensembles (2021.findings-acl)
Copied to clipboard
| Challenge: | Many task-oriented dialogue systems use deep reinforcement learning (DRL) to learn policies that respond to the user appropriately and complete the tasks successfully. |
| Approach: | They propose a method to diversify dialogues using a set of user models by constraining the intensity to interact with diverse user models. |
| Outcome: | The proposed method improves the performance of several state-of-the-art DRL dialogue agents trained in simulators. |
Structured Refinement for Sequential Labeling (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing work on identifying target-irrelevant information relies on locally normalized attention without considering possible labels at other time steps. |
| Approach: | They propose to extend local normalized attention to leverage structural information for refinement . they propose to use two implementation tricks to accelerate CRF computation and an initialization trick for Chinese character embeddings . |
| Outcome: | The proposed method can be extended to include Chinese character embeddings and two implementation tricks to accelerate CRF computation. |
End-to-End Construction of NLP Knowledge Graph (2021.findings-acl)
Copied to clipboard
| Challenge: | a new schema for NLP knowledge about tasks, datasets and metrics is proposed. |
| Approach: | They propose a new schema that represents knowledge about tasks, datasets and metrics in the NLP domain. |
| Outcome: | The proposed framework can be automatically built into scientific leaderboards . the proposed system achieves reasonable results for all relation types on this small-scale graph . |
Deciphering Implicit Hate: Evaluating Automated Detection Algorithms for Multimodal Hate (2021.findings-acl)
Copied to clipboard
| Challenge: | Imlicit hate content has unusual syntax, polysemic words, and fewer markers of prejudice, e.g., slurs . multimodal content is harder to detect than unimodal content, such as memes . |
| Approach: | They evaluate the role of semantic and multimodal context for detecting implicit and explicit hate . they find that all models perform better on content with full annotator agreement . |
| Outcome: | The proposed model outperforms other models on implicit and explicit hate detection tasks because of its lower propensity towards false positives. |
Studying the Evolution of Scientific Topics and their Relationships (2021.findings-acl)
Copied to clipboard
| Challenge: | a study of scientific topics and their evolution through time is proposed . we analyze scientific texts published in the field of computational linguistics . |
| Approach: | They propose a multidimensional approach to studying scientific topics through time and their relationships between them. |
| Outcome: | The proposed model analyzes scientific texts published in the ACL Anthology and compares them with case studies to understand how topics evolve and disappear over time. |
End-to-End Self-Debiasing Framework for Robust NLU Training (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models incorporate dataset biases leading to strong performance on in-distribution test sets but poor performance on out-of-distortion (OOD) tests. |
| Approach: | They propose a debiasing framework where the shallow representations of the main model are used to derive a bias model and both models are trained simultaneously. |
| Outcome: | The proposed framework outperforms existing approaches on three well-studied NLU tasks while still delivering high in-distribution performance. |
A Mixed-Method Design Approach for Empirically Based Selection of Unbiased Data Annotators (2021.findings-acl)
Copied to clipboard
| Challenge: | Current approaches to selecting annotators are limited at the policy-guidance level, rendering them unusable for machine learning practitioners. |
| Approach: | They propose a method that is functional, adaptable, and simpler to implement in selecting unbiased annotators for any machine learning problem. |
| Outcome: | The proposed approach is functional, adaptable, and simpler to implement on a real-world geopolitical problem. |
An Evaluation of Disentangled Representation Learning for Texts (2021.findings-acl)
Copied to clipboard
| Challenge: | Disentangled representations of texts encode information pertaining to different aspects of the text in separate vector embeddings. |
| Approach: | They propose to use a highly-structured natural language dataset to evaluate disentangled representations for texts. |
| Outcome: | The proposed models are well-suited for learning disentangled representations of texts on a synthetic natural language dataset. |
Injecting Knowledge Base Information into End-to-End Joint Entity and Relation Extraction and Coreference Resolution (2021.findings-acl)
Copied to clipboard
| Challenge: | Using unsupervised entity linking, we solve named entity recognition, coreference resolution and relation extraction tasks together. |
| Approach: | They propose to use a knowledge base to inject information into a joint IE model by using unsupervised entity linking. |
| Outcome: | The proposed model improves on two datasets with 5% F1 score. |
Knowing More About Questions Can Help: Improving Calibration in Question Answering (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing work on calibration focuses on model confidence, such as the max probability of the predicted class. |
| Approach: | They propose a calibration method which estimates whether model correctly predicts answer for each question. |
| Outcome: | The proposed calibration method achieves 5-10% gains on reading comprehension benchmarks. |
Enhancing Metaphor Detection by Gloss-based Interpretations (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to metaphor detection are limited by ambiguous meanings of metaphorical substitute words. |
| Approach: | They propose a model that utilizes glosses to interpret metaphorical words by enhancing three datasets with gloss annotations. |
| Outcome: | The proposed model outperforms state-of-the-art models on three enhanced datasets and that gloss-based interpretation benefits metaphor detection. |
Evaluating Word Embeddings with Categorical Modularity (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing word embeddings use different bilingual supervision signals with varying levels of strength. |
| Approach: | They propose a graph modularity metric to measure word embedding quality . they use a set of 500 words belonging to 59 neurobiologically motivated semantic categories . |
| Outcome: | The proposed metric measures word embedding quality on monolingual and cross-lingual tasks. |
Attention-based Contextual Language Model Adaptation for Speech Recognition (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing language models do not incorporate utterance level contextual information . however, for some domains like voice assistants, additional context provides a rich input signal . |
| Approach: | They propose a method for training neural speech recognition models on text and contextual data. |
| Outcome: | The proposed model reduces perplexity by 7.0% relative over a standard LM . it also improves perxicity by 2.8% relative to a state-of-the-art model for contextual LM. |
Annotation and Evaluation of Coreference Resolution in Screenplays (2021.findings-acl)
Copied to clipboard
| Challenge: | Screenplays refer to characters using different names, pronouns, and nominal expressions. |
| Approach: | They develop an automatic screenplay parser to extract structural information and design coreference rules based upon the structure of screenplays. |
| Outcome: | The proposed model outperforms a benchmark model on the screenplay coreference resolution task. |
Exploring Cross-Lingual Transfer Learning with Unsupervised Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | a new CLTL model is proposed to facilitate cross-linguistic transfer learning between distant languages . a key to CLTL is to learn a shared representation space for the given source-target language pair. |
| Approach: | They propose a new CLTL model that integrates machine translation with MT . they use an unannotated data technique to make use of the model's pre-training and fine-tuning . |
| Outcome: | The proposed model achieves better CLTL performance than the baseline model without more annotated data. |
Pipeline Signed Japanese Translation Focusing on a Post-positional Particle Complement and Conjugation in a Low-resource Setting (2021.findings-acl)
Copied to clipboard
| Challenge: | a pipeline translation method is proposed to take advantage of the similarities and differences between sign language and spoken language. |
| Approach: | They propose a pipeline translation method that takes advantage of similarities between spoken and spoken Japanese . they map glosses to spoken language words and train them using a monolingual Japanese corpus . |
| Outcome: | The proposed method performs robustly on the low-resource corpus and is +4.4/+4.9 points above baseline. |
Language-Mediated, Object-Centric Representation Learning (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent work has studied the problem of unsupervised object representation learning, though without language. |
| Approach: | They propose language-mediated, Objectcentric Representation Learning (LORL) a paradigm for learning disentangled, objectcentric scene representations from vision and language. |
| Outcome: | The proposed paradigm improves performance of unsupervised object discovery algorithms on two datasets using language. |
Entheos: A Multimodal Dataset for Studying Enthusiasm (2021.findings-acl)
Copied to clipboard
| Challenge: | Enthusiasm is an important part of engaging communication. |
| Approach: | They propose a multimodal dataset for studying enthusiasm composed of video, audio, and text. |
| Outcome: | The proposed model shows that pitch, loudness, and discourse relation parsing are important in distinguishing enthusiastic communication. |
Are Rotten Apples Edible? Challenging Commonsense Inference Ability with Exceptions (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have shown that pre-trained language models encode commonsense relational knowledge, but they are often insensitive to context, ignoring overt contextual cues such as negations. |
| Approach: | They propose a procedure that exploits generic associations in masked language models to create model-specific entailment schemas. |
| Outcome: | The proposed procedure exploits generic associations in masked language models to create model-specific Winograd-style entailment schemas. |
GRICE: A Grammar-based Dataset for Recovering Implicature and Conversational rEasoning (2021.findings-acl)
Copied to clipboard
| Challenge: | a grammar-based dialogue dataset, GRICE, is designed to bring implicature into pragmatic reasoning in conversations . implicature recovery is a key component of open-ended dialogue reasoning . |
| Approach: | They propose a grammar-based dialogue dataset to bring implicature into pragmatic reasoning . they use a hierarchical grammar model to generate the entire dataset . |
| Outcome: | The proposed model shows a significant performance gap between baseline methods and human models . the model shows an overall performance boost in conversational reasoning . |
RetroGAN: A Cyclic Post-Specialization System for Improving Out-of-Knowledge and Rare Word Representations (2021.findings-acl)
Copied to clipboard
| Challenge: | Retrofitting is a technique used to move word vectors closer together or further apart in their space to reflect their relationships in a Knowledge Base (KB). |
| Approach: | They propose a system that uses two GANs to learn a one-to-one mapping between concepts and retrofitted counterparts. |
| Outcome: | The proposed system performs well on word-similarity benchmarks and a sentence simplification task. |
Fusion: Towards Automated ICD Coding via Feature Compression (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to assign ICD codes from unstructured clinical notes are noisy and prone to errors. |
| Approach: | They propose a feature compressed ICD coding model called Fusion to address this problem. |
| Outcome: | The proposed model outperforms existing models on two widely used datasets. |
Automatic Document Sketching: Generating Drafts from Analogous Texts (2021.findings-acl)
Copied to clipboard
| Challenge: | Large pre-trained language models have made it possible to make high-quality predictions on how to add or change a sentence in a document. |
| Approach: | They propose a task to generate entire draft documents for the writer to review and revise. |
| Outcome: | The proposed model can make high-quality predictions on how to add or change a sentence in a document, but it lacks the branching factor to offer useful editing suggestions at a global or document level. |
Trade the Event: Corporate Events Detection for News-Based Event-Driven Trading (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models that use textual features and sentiments to make stock predictions are poor explainability and low signal-to-noise ratio. |
| Approach: | They propose a bi-level event detection model that detects corporate events from news articles and an elaborately-annotated dataset EDT for corporate event detection and news-based stock prediction benchmark. |
| Outcome: | The proposed strategy outperforms baselines in winning rate, excess returns over the market, and the average return on each transaction. |
Language-based General Action Template for Reinforcement Learning Agents (2021.findings-acl)
Copied to clipboard
| Challenge: | Prior knowledge is important in decision-making, and humans preserve it in the form of natural language (NL). |
| Approach: | They propose an environmentagnostic action framework that incorporates prior knowledge into decision-making . they propose to use general semantic schemes to facilitate agent in finding plausible actions . |
| Outcome: | The proposed agent performs better than agents that rely on gamespecific actions. |
MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing work on deep self-attention distillation for natural language processing tasks is limited by computational resources and latency. |
| Approach: | They generalize deep self-attention distillation in MINILM by using only self- attention relation distillation for taskagnostic compression of pretrained Transformers. |
| Outcome: | The proposed model outperforms the state-of-the-art in a multilingual and multilingual teacher model. |
Attending via both Fine-tuning and Compressing (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies show that attention mechanisms can improve models' interpretation, but they are not explicable. |
| Approach: | They propose a framework consisting of a learner and a compressor to purify attention scores . they propose to fine-tune and compress the attention mechanism to obtain a more faithful explanation . |
| Outcome: | The proposed framework improves performance and interpretability on eight benchmark datasets. |
Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for event causality identification (ECI) rely on labeled data, but the scale of annotated datasets is limited. |
| Approach: | They propose a self-supervised framework to learn context-specific causal patterns from external causal statements and adopt a contrastive transfer strategy to incorporate the learned context- specific causal patterns into the target ECI model. |
| Outcome: | The proposed method significantly outperforms existing methods on EventSto-ryLine and Causal-TimeBank (+2.0 and +3.4 points on F1 value respectively). |
PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval (2021.findings-acl)
Copied to clipboard
Ruiyang Ren, Shangwen Lv, Yingqi Qu, Jing Liu, Wayne Xin Zhao, QiaoQiao She, Hua Wu, Haifeng Wang, Ji-Rong Wen
| Challenge: | Recent studies only consider query-centric similarity relation when learning the dual-encoder retriever. |
| Approach: | They propose a query-centric and PAssage-centric approach to capture more comprehensive similarity relations for dense passage retrieval. |
| Outcome: | The proposed approach significantly outperforms existing models on both MSMARCO and Natural Questions datasets. |
Is Human Scoring the Best Criteria for Summary Evaluation? (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on summary quality measure have shown that it correlates well with quality scores produced by human annotators. |
| Approach: | They propose to use a criterion that does not rely on human scores to judge summary quality . they propose to develop a method that can be used to determine the best measure from a family of measures . |
| Outcome: | The proposed measure could be used to determine the best summary quality measure from a family of measures. |
Assessing Dialogue Systems with Distribution Distances (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation metrics focus on turnlevel quality, which is not well suited for open-end dialogue tasks. |
| Approach: | They propose to measure the performance of a dialogue system by computing the distributionwise distance between its generated conversations and real-world conversations. |
| Outcome: | The proposed metrics correlate better with human judgments than existing metrics on dialogue systems. |
Neural Combinatory Constituency Parsing (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to constituency parsing are based on symbolic engineering, but they are simplified by their adaptive distributed representation. |
| Approach: | They propose two fast combinatory models for constituency parsing: binary and multibranching. |
| Outcome: | The proposed models achieve an F1 score of 92.54 on Penn Treebank, speeding at 1327.2 sents/sec. |
Learning Shared Semantic Space for Speech-to-Text Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | End-to-end speech translation (ST) has been treated as an independent task . however, the modality gap has rendered MT data and its end-to end models incompatible with their ST counterparts. |
| Approach: | They propose to bridge the representation gap between text and audio inputs by projecting audio and text features to a common semantic representation. |
| Outcome: | The proposed model improves performance on two ST benchmarks and achieves 27.1 BLEU on MuST-C EN-DE. |
Empowering Language Understanding with Counterfactual Reasoning (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for language understanding use the recognized patterns in the testing phase that are inherently different from us humans who have counterfactual thinking. |
| Approach: | They propose a counterfactual Reasoning Model which mimics counterfactive thinking by learning from few counterffact samples. |
| Outcome: | The proposed model can detect and make predictions from textual patterns . it can also detect negative sarcastic puns by comparing them with imaginations . |
Knowledge-Empowered Representation Learning for Chinese Medical Reading Comprehension: Task, Model and Resources (2021.findings-acl)
Copied to clipboard
| Challenge: | MRC is a popular task in NLP, aiming to understand a passage and answer the relevant questions. |
| Approach: | They propose a multi-target machine learning task for the medical domain that predicts answers to medical questions and corresponding support sentences from medical information sources simultaneously. |
| Outcome: | The proposed model outperforms baselines by fusing context-aware and knowledge-awful token representations. |
Correcting Chinese Spelling Errors with Phonetic Pre-training (2021.findings-acl)
Copied to clipboard
Ruiqing Zhang, Chao Pang, Chuanqiang Zhang, Shuohuan Wang, Zhongjun He, Yu Sun, Hua Wu, Haifeng Wang
| Challenge: | Existing methods for Chinese spelling correction only use pre-trained language model or incorporate phonological information as external knowledge. |
| Approach: | They propose a phonetic Chinese spelling correction model that integrates phonetic features into language model by leveraging pre-training and fine-tuning methods. |
| Outcome: | The proposed model outperforms existing methods on SIGHAN datasets and improves on other datasets. |
Multi-Lingual Question Generation with Language Agnostic Language Model (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing training data for question generation in English and Chinese is limited . a language-agnostic model is developed to learn the shared representation from several languages in a single architecture. |
| Approach: | They propose a language-agnostic language model which learns the shared representation from several languages in a single architecture. |
| Outcome: | The proposed model improves multi-lingual question generation over five languages. |
Structure-Aware Pre-Training for Table-to-Text Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Pretraining techniques have achieved great success on table-to-text generation. |
| Approach: | They propose a pre-trained model that is trained with tables and their contexts to generate fluent text from table input. |
| Outcome: | The proposed model can understand the structured input table and generate fluent text. |
On the Interplay Between Fine-tuning and Composition in Transformers (2021.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained transformer language models have shown remarkable performance on a variety of NLP tasks. |
| Approach: | They propose to fine-tune transformer language models on a paraphrase and sentiment task and analyze their results to determine whether they benefit compositionality. |
| Outcome: | The proposed model performance on a paraphrase and sentiment task is compared with pre-trained models on lexical-level representations. |
Lifelong Learning of Topics and Domain-Specific Word Embeddings (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing lifelong topic models focus on indomain text streams in which each chunk only contains documents from a single domain. |
| Approach: | They develop a lifelong collaborative model that uses non-negative matrix factorization to learn topics and domain-specific word embeddings. |
| Outcome: | The proposed model can learn topics and domain-specific word embeddings from a lifelong collaborative model. |
Leveraging Argumentation Knowledge Graph for Interactive Argument Pair Identification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing researches focus on sentence matching but the interaction of opinions requires reasoning of knowledge, which is beyond textual information. |
| Approach: | They propose to leverage external knowledge to enhance the identification of interactive argument pairs by analyzing the discussion thread of the target topic in an online forum. |
| Outcome: | The proposed model achieves state-of-the-art in the benchmark dataset. |
A Multi-Task Learning Framework for Multi-Target Stance Detection (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models fail to learn target-specific representations and are prone to overfitting. |
| Approach: | They propose a multi-task learning network to train one model on all target pairs . their results show that their proposed model outperforms the best-performing baseline by 12.39% . |
| Outcome: | The proposed model outperforms the best-performing baseline model by 12.39% in macro-averaged F1-score. |
Confidence-Aware Scheduled Sampling for Neural Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Neural machine translation models are trained to maximize the likelihood of the next token given previous golden tokens as inputs, but at the inference stage, golden token is unavailable. |
| Approach: | They propose a scheduled sampling method that randomly replaces groundtruth tokens with predicted ones during training, ignoring real-time model competence. |
| Outcome: | The proposed method outperforms the Transformer and vanilla scheduled sampling on large-scale translations. |
MA-BERT: Learning Representation by Incorporating Multi-Attribute Knowledge in Transformers (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for incorporating external attribute knowledge into deep neural networks are concatenating multiple attributes to word/text representation or treating them as biases to adjust attention distribution. |
| Approach: | They propose a multi-attribute BERT to incorporate external attribute knowledge into deep neural networks. |
| Outcome: | The proposed method outperforms existing models and models on three benchmark datasets. |
A Closer Look into the Robustness of Neural Dependency Parsers Using Better Adversarial Examples (2021.findings-acl)
Copied to clipboard
| Challenge: | Neural network-based models have been successful in a wide range of NLP tasks, but their performance is undermined by adversarial examples that would pose no confusion for humans. |
| Approach: | They propose a method to generate high-quality adversarial examples with a higher number of candidate generators and stricter filters and then verify their quality using automatic and human evaluations. |
| Outcome: | The proposed method improves the robustness of English parsing models by relying on adversarial training and model ensembling. |
P-Stance: A Large Dataset for Stance Detection in Political Domain (2021.findings-acl)
Copied to clipboard
| Challenge: | stance detection is a method to determine whether a text author is in favor of, against or neutral toward a specific target. |
| Approach: | They propose to use a large stance detection dataset in the political domain to detect stances on twitter. |
| Outcome: | The proposed model achieves a macro-average F1-score of 80.53% and can be used to improve cross-domain stance detection. |
WIND: Weighting Instances Differentially for Model-Agnostic Domain Adaptation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for instance weighting cannot learn the weights which make the model generalize well in target domain. |
| Approach: | They propose a modelagnostic instance weighting algorithm which can learn the instance weights instead of manually designed weighting metrics. |
| Outcome: | The proposed method can learn the instance weights instead of manually designed weighting metrics. |
DocOIE: A Document-level Context-Aware Dataset for OpenIE (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing solutions focus on extracting tuples at sentence level, but sentences exist as part of a document rather than standalone. |
| Approach: | They propose to annotate 800 sentences from 80 documents to form a DocOIE dataset . they propose to use document-level context to improve OpenIE performance . |
| Outcome: | The proposed OpenIE model improves performance by incorporating documentlevel context into the dataset. |
Event Extraction from Historical Texts: A New Dataset for Black Rebellions (2021.findings-acl)
Copied to clipboard
| Challenge: | Using EE to extract historical data, we study the discourse of slave and non-slave African diaspora rebellions published in the periodical press in this period. |
| Approach: | They propose a dataset to detect event trigger words and their arguments in nineteenth-century newspapers. |
| Outcome: | The proposed dataset features 5 entity types, 12 event types, and 6 argument roles that concern slavery and black movements between the eighteenth and nineteenth centuries. |
Zero-shot Medical Entity Retrieval without Annotation: Learning From Rich Knowledge Graph Semantics (2021.findings-acl)
Copied to clipboard
| Challenge: | Current approaches to medical entity retrieval generalize poorly to unseen sub-specialties . zero-shot retrieval is challenging due to the high degree of ambiguity and variability in medical corpora . |
| Approach: | They propose a set of learning tasks designed to train efficient zero-shot entity retrieval models. |
| Outcome: | The proposed architecture outperforms common zero-shot benchmarks with 7% to 30% higher recall across multiple major medical ontologies. |
CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection (2021.findings-acl)
Copied to clipboard
Henry Weld, Guanghao Huang, Jean Lee, Tongshu Zhang, Kunze Wang, Xinghong Guo, Siqu Long, Josiah Poon, Caren Han
| Challenge: | Existing toxic language detection models focus on the single utterance level without deeper understanding of context. |
| Approach: | They propose a dataset for in-game toxic language detection enabling joint intent classification and slot filling analysis, which is the core task of Natural Language Understanding (NLU). |
| Outcome: | The proposed framework handles utterance and token-level patterns, and rich contextual chatting history. |
Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection (2021.findings-acl)
Copied to clipboard
| Challenge: | Event detection typically does not have sufficient labelled data, thus can be formulated as a few-shot learning problem. |
| Approach: | They propose a knowledge-based fewshot event detection method which introduces external event knowledge as the knowledge prior of event types. |
| Outcome: | Experiments show that the proposed method outperforms baselines by 15 F 1 points . event detection is an important task in information extraction . |
Stylized Story Generation with Style-Guided Planning (2021.findings-acl)
Copied to clipboard
| Challenge: | Current storytelling systems focus more on generating stories with coherent plots regardless of the narration style. |
| Approach: | They propose a novel task, stylized story generation, that first plans stylized keywords and then generates the whole story with the guidance of the keywords. |
| Outcome: | The proposed model can generate emotion-driven or event-driven stories based on the ROCStories dataset . |
Dynamic Connected Networks for Chinese Spelling Check (2021.findings-acl)
Copied to clipboard
| Challenge: | Chinese spelling check (CSC) is a task to detect and correct spelling errors in Chinese text. |
| Approach: | They propose a new architecture which generates Chinese characters via a Pinyin Enhanced Candidate Generator and then utilizes an attention-based network to model the dependencies between two adjacent Chinese characters. |
| Outcome: | The proposed method achieves state-of-the-art performance on three human-annotated datasets. |
A Multi-Level Attention Model for Evidence-Based Fact Checking (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent state-of-the-art approaches have developed increasingly sophisticated models based on graph structures. |
| Approach: | They propose a simple model that can be trained on sequence structures and can benefit from joint training. |
| Outcome: | The proposed model outperforms the graph-based models on a large-scale dataset for Fact Extraction and VERification. |
RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer (2021.findings-acl)
Copied to clipboard
| Challenge: | End-to-end simultaneous speech translation (SST) is useful in many scenarios but has not been fully investigated. |
| Approach: | They propose an end-to-end simultaneous speech translation model called RealTranS . they use interleaved convolution and unidirectional Transformer layers to downsample input speech . |
| Outcome: | The proposed model outperforms existing models on public and widely-used datasets in multiple latency settings. |
Training ELECTRA Augmented with Multi-word Selection (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing pre-training methods for NLP tasks require massive computation resources. |
| Approach: | They propose a method that trains a discriminator to detect replaced tokens and select original tokens from candidate sets. |
| Outcome: | The proposed method improves ELECTRA based on multi-task learning on GLUE and SQUAD datasets. |
REAM♯: An Enhancement Approach to Reference-based Evaluation Metrics for Open-domain Dialog Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation metrics for open-domain dialogue systems are limited by the diversity of possible outcomings. |
| Approach: | They propose a method to augment a reference set to improve reliability . they propose BLEU to measure similarity between a predicted response and a small set of references . |
| Outcome: | The proposed model improves the reliability of reference-based metrics with augmented reference sets. |
Relation Extraction with Type-aware Map Memories of Word Dependencies (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on the dependency connections between words with limited attention paid to exploiting dependency types. |
| Approach: | They propose a neural approach for relation extraction with type-aware map memories . they map all associated words along with dependencies among them to memory slots . |
| Outcome: | The proposed approach achieves state-of-the-art on two English benchmark datasets. |
PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning (2021.findings-acl)
Copied to clipboard
| Challenge: | PLATO-2 is a high-quality open-domain chatbot that can generate one-to-many mappings and improve response quality. |
| Approach: | They propose a curriculum learning process to build a high-quality open-domain chatbot . they use a coarse-grained generation model and latent variables to train a generative model . |
| Outcome: | The proposed model improves on Chinese and English data and can generate diverse responses and select the best response. |
JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing pre-trained models for knowledgegraph-to-text generation ignore graph structure during encoding and lack elaborate pre-training tasks to explicitly model graph-text alignments. |
| Approach: | They propose a graph-text joint representation learning model called JointGT which incorporates a structure-aware semantic aggregation module into each Transformer layer to preserve the graph structure. |
| Outcome: | The proposed model achieves state-of-the-art performance on various KG-to-text datasets. |
AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | End-to-end speech translation models learn acoustic representations from the encoder, which is not desirable for cross-modal and cross-lingual translation. |
| Approach: | They propose an adaptive speech-to-text translation model that dynamically adapts acoustic states in the decoder. |
| Outcome: | The proposed model outperforms state-of-the-art speech translation models on two widely-used datasets. |
OKGIT: Open Knowledge Graph Link Prediction with Implicit Types (2021.findings-acl)
Copied to clipboard
| Challenge: | Open Knowledge Graphs (OpenKGs) are sparse and not directly usable in an end task. |
| Approach: | They propose a method that bootstraps OpenKGs from a corpus using OpenIE tools. |
| Outcome: | The proposed method achieves state-of-the-art performance while producing type compatible NPs in the link prediction task. |
Multimodal Fusion with Co-Attention Networks for Fake News Detection (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to detect fake news with textual and visual contents are ineffective because they concatenate unimodal features without considering inter-modality relations. |
| Approach: | They propose to fuse textual and visual features for fake news detection using multimodal co-attention networks to learn inter-dependencies between multimodal features. |
| Outcome: | Extensive experiments on two realworld datasets show that the proposed network outperforms state-of-the-art methods and learns inter-dependencies among multimodal features. |
Joint Multi-Decoder Framework with Hierarchical Pointer Network for Frame Semantic Parsing (2021.findings-acl)
Copied to clipboard
| Challenge: | Current researches on frame semantic parsing ignore the interactions among subtasks. |
| Approach: | They propose a multi-decoder strategy to handle these subtasks together . they propose introducing a hierarchical pointer network for argument identification . |
| Outcome: | The proposed architecture improves on state-of-the-art models on FrameNet dataset. |
H-FND: Hierarchical False-Negative Denoising for Distant Supervision Relation Extraction (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing work on distant supervision denoising introduces false-positive (FP) and falsenegative (FN) training instances to the generated datasets. |
| Approach: | They propose a hierarchical false-negative denoising framework for distant supervision relation extraction that denoises false-positive and false- negative training instances. |
| Outcome: | The proposed framework can revise FN instances correctly and maintain high F1 scores even when 50% of instances have been turned into negatives. |
GEM: A General Evaluation Benchmark for Multimodal Tasks (2021.findings-acl)
Copied to clipboard
Lin Su, Nan Duan, Edward Cui, Lei Ji, Chenfei Wu, Huaishao Luo, Yongfei Liu, Ming Zhong, Taroon Bharti, Arun Sacheti
| Challenge: | Existing datasets that focus on natural language tasks are not considered as a general evaluation benchmark for multimodal tasks. |
| Approach: | They present a general evaluation benchmark for multimodal tasks, GEM 1 . they compare it with existing multimodal vision-language datasets . |
| Outcome: | The proposed model is compared with existing vision-language datasets focusing on natural language tasks . it is the largest vision-linguistic dataset covering image-language tasks and video-language task at the same time . |
Graph Relational Topic Model with Higher-order Graph Attention Auto-encoders (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for learning low-dimensional representations of networked documents are largely ignored for document networks. |
| Approach: | They propose a graph relational topic model to explore document neighborhood information . the model can learn efficient networked document representations in the latent topic space . |
| Outcome: | The proposed model outperforms existing methods on unsupervised representation learning and other downstream tasks. |
Paths to Relation Extraction through Semantic Structure (2021.findings-acl)
Copied to clipboard
| Challenge: | Syntactic and semantic structure directly reflect relations expressed by the text at hand and are therefore very useful for relation extraction (RE) |
| Approach: | They propose two methods for integrating broad-coverage semantic structure into supervised RE models by encoding semantic DAGs. |
| Outcome: | The proposed methods overshadow the use of syntactic integrations in RE . they reduce UCCA into a bilexical structure and encode semantic DAG structures . |
Dynamic and Multi-Channel Graph Convolutional Networks for Aspect-Based Sentiment Analysis (2021.findings-acl)
Copied to clipboard
| Challenge: | . - (EN) |
| Approach: | . - (EN) |
| Outcome: | . - (EN) |
Automatic Text Simplification for Social Good: Progress and Challenges (2021.findings-acl)
Copied to clipboard
| Challenge: | ATS has been promoted as a natural language processing task since the 1990s . but since 2010, the field has been focusing on building complex end-to-end neural architectures based on ATS . |
| Approach: | They propose to use automated text simplification (ATS) to make texts more accessible to people with disabilities . they argue that lack of high-quality TS datasets and standardized evaluation procedures are barriers . |
| Outcome: | The proposed neural ATS systems are based on a new set of TS datasets and a standardized evaluation procedure. |
A Neural Edge-Editing Approach for Document-Level Relation Graph Extraction (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to extract relation information from documents do not capture interactions between entities. |
| Approach: | They propose an iterative approach to extract relation information from a document . they initialize relation graphs using a pretrained transformer model and a graph convolutional neural network model . |
| Outcome: | The proposed method extracts relation information from a document using a rule-based system and empty graphs. |
Dialogue-oriented Pre-training (2021.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models (PrLMs) have shown impressive improvements for various downstream tasks including various dialogue related ones. |
| Approach: | They propose to use pre-trained language models to simulate dialogue features on general plain text with common language model training objectives to improve performance. |
| Outcome: | The proposed method is fine-tuned on three public multi-turn dialogue datasets and achieves significant and consistent improvement over the plain PrLMs. |
GrantRel: Grant Information Extraction via Joint Entity and Relation Extraction (2021.findings-acl)
Copied to clipboard
| Challenge: | a funder name refers to an agency, organization, or program providing financial support for the research. |
| Approach: | They propose a funding sentence classifier and a relation extraction framework to extract grant information from scientific articles. |
| Outcome: | The proposed framework outperforms state-of-the-art BERT-based RE baselines against the PubMed Central and arXiv test sets. |
Enhancing Language Generation with Effective Checkpoints of Pre-trained Language Model (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to exploit PrLMs for NLG tasks do not get as much performance gain as in the NLU task. |
| Approach: | They propose a method to integrate public checkpoints of PrLMs for the most convenience. |
| Outcome: | The proposed method significantly improves the quality of the language generation tasks on 6 different kinds of PrLMs. |
Making Flexible Use of Subtasks: A Multiplex Interaction Network for Unified Aspect-based Sentiment Analysis (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies aim to integrate multiple sub-tasks into a unified ABSA model but suffer from major disadvantages . |
| Approach: | They propose a multi-task learning approach to make use of sub-tasks for a unified ABSA. |
| Outcome: | The proposed model can work well when some sub-tasks are absent, and the interactive relations among subtasks not adequate. |
Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | a lack of data in low-resource languages has limited the performance of a multilingual pre-trained model. |
| Approach: | They propose a continuous pre-training framework to adapt mBART to unseen languages . they construct noisy mixed-language text from the monolingual corpus of the target language . |
| Outcome: | The proposed framework improves finetuning performance on low-resource translation pairs . the proposed framework also improves on translation pairs where both languages are seen . |
Transformer-Exclusive Cross-Modal Representation for Vision and Language (2021.findings-acl)
Copied to clipboard
| Challenge: | a number of approaches to crossmodal representation have been used, but transformer architecture has taken over the recurrent neural networks in natural language processing tasks. |
| Approach: | They propose to use transformer architecture to handle cross-modal representations for vision and language with compatible performance to convolutional neural networks. |
| Outcome: | The proposed model outperforms recurrent neural networks in vision and language representations with transformer architecture. |
Two Parents, One Child: Dual Transfer for Low-Resource Neural Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Neural machine translation suffers when parallel data is scarce for training . a new framework to transfer multiple sources of auxiliary data is proposed . |
| Approach: | They propose a framework to transfer multiple sources of auxiliary data from high-resource parallel data to low-resourced translation models using pretrained language models. |
| Outcome: | The proposed approach yields consistent improvements over strong competitors for multiple translation directions. |
Contrastive Aligned Joint Learning for Multilingual Summarization (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing summarization systems for multilingual text summarizing are limited due to the lack of large-scale data in multiple languages. |
| Approach: | They propose a multilingual summarization system that can understand documents in multiple languages and generate summaries in the corresponding language. |
| Outcome: | The proposed model improves over monolingual models in all languages and transferable to other languages. |
When Time Makes Sense: A Historically-Aware Approach to Targeted Sense Disambiguation (2021.findings-acl)
Copied to clipboard
Kaspar Beelen, Federico Nanni, Mariona Coll Ardanuy, Kasra Hosseini, Giorgia Tolfo, Barbara McGillivray
| Challenge: | a new paper examines whether making NLP models sensitive to time improves their performance . timesensitive Sense Disambiguation is a variation on Word Sense disambiguation . authors present a task to determine whether a token in a text is related to a specific sense . |
| Approach: | They propose a task to determine whether a token in a text is related to a specific sense of a lemma. |
| Outcome: | The proposed model improves when time sensitive, rather than historically-aware, models . the proposed model is a variation on Word Sense Disambiguation (WSD) the proposed method is of more practical relevance to digital history and cultural analysis . |
Understanding Feature Focus in Multitask Settings for Lexico-semantic Relation Identification (2021.findings-acl)
Copied to clipboard
| Challenge: | Lexico-semantic relations embody symmetric and asymmetric linguistic phenomena such as synonymy (e.g. phone telephone), cohyponymy (, cohypoonymy, hypernymy, meronymy) and more can be enumerated. |
| Approach: | They propose to combine feature engineering and multitask architectures to identify lexico-semantic relations by combining asymmetric distributional features with shared-private models. |
| Outcome: | The proposed models improve over binary and fully-shared classifiers and balance the focus on features between private and shared layers 1 and 2 . |
Don’t Miss the Labels: Label-semantic Augmented Meta-Learner for Few-Shot Text Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on building a meta-learner from input text but ignore abundant semantic information beneath class labels. |
| Approach: | They propose a framework to make full use of label semantics in few-shot text classification systems. |
| Outcome: | The proposed framework can be plugged into the existing few-shot text classification system. |
Detecting Harmful Memes and Their Targets (2021.findings-acl)
Copied to clipboard
Shraman Pramanick, Dimitar Dimitrov, Rituparna Mukherjee, Shivam Sharma, Md. Shad Akhtar, Preslav Nakov, Tanmoy Chakraborty
| Challenge: | a growing body of research on meme analysis has focused on detecting harmful memes and their social entities . a meme is a form of content that is often harmless and designed to look funny . but its multimodal nature and camouflaged semantics make its analysis challenging . |
| Approach: | They propose to use multimodal models to detect harmful memes and identify social entities that harmful meme targets. |
| Outcome: | The proposed model can detect harmful memes and the social entities they target . the proposed model lacks the appropriate contexts and is poorly validated . |
Progressive Multi-Granularity Training for Non-Autoregressive Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Non-autoregressive translation models are weak at learning high-mode knowledge, argues a new study . despite the improved learning difficulty, there are still complicated word orders and structures in the synthetic sentences, making the NAT performance sub-optimal. |
| Approach: | They propose to train non-autoregressive translation models to learn fine-grained lower-mode knowledge . they break down sentence-level examples into three types and increase granularities . |
| Outcome: | The proposed method improves phrase translation accuracy and model reordering ability against strong NAT baselines. |
ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in NLP focus on large annotated training data. |
| Approach: | They propose an unsupervised framework that does not use parallel or pseudo-parallel/back-translated data. |
| Outcome: | The proposed framework does not use parallel or pseudo-parallel/back-translated data. |
HacRED: A Large-Scale Relation Extraction Dataset Toward Hard Cases in Practical Applications (2021.findings-acl)
Copied to clipboard
Qiao Cheng, Juntao Liu, Xiaoye Qu, Jin Zhao, Jiaqing Liang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan, Yanghua Xiao
| Challenge: | Relation extraction (RE) is an essential topic in natural language processing and has attracted extensive attention. |
| Approach: | They propose a case-oriented construction framework to build a hard case relation extraction dataset with 65,225 relational facts annotated from 9,231 documents. |
| Outcome: | The proposed model achieves a high 96% F1 score on data quality and is far lower than humans. |
Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads? (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent studies on multilingual representations focus on whether there is an emergence of language-independent representations or whether multilingual models partition their weights among different languages. |
| Approach: | They analyze encoder self-attention and encoder-decoder attention heads in a multilingual neural translation model. |
| Outcome: | The proposed model is based on a multilingual neural translation model with a language-independent representation. |
Learning Sequential and Structural Information for Source Code Summarization (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models that learn both sequential and structural features of source code are limited in their use. |
| Approach: | They propose a model that learns both the sequential and the structural features of code for source code summarization. |
| Outcome: | The proposed model outperforms the state-of-the-art for source code summarization by experiments and human evaluations. |
Energy-based Unknown Intent Detection with Data Manipulation (2021.findings-acl)
Copied to clipboard
| Challenge: | Unknown intent detection aims to identify the out-of-distribution (OOD) utterance whose intent has never appeared in the training set. |
| Approach: | They propose a framework to generate high-quality OOD utterances with importance weighTs (GOT) their framework is fine-tuned to detect out-of-distribution utterrances . |
| Outcome: | The proposed framework can achieve state-of-the-art results on two benchmark datasets. |
Automatic Rephrasing of Transcripts-based Action Items (2021.findings-acl)
Copied to clipboard
| Challenge: | a growing number of online meetings are transcribed using automated speech recognition systems. |
| Approach: | They propose to use annotated transcripts to generate a human-level rephrasing of an action item . they use supervised text generation techniques and pre-trained transformer models to train models . |
| Outcome: | The proposed model generates a human-level rephrasing of an action item in annotated meeting transcripts. |
MergeDistill: Merging Language Models using Pre-trained Distillation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing pre-trained multilingual language models often lack capacity and skewed data . this leads to inequitable representation of languages due to limited capacity and sub-optimal vocabularies. |
| Approach: | They propose a framework to merge pre-trained multilingual language models to maximize their assets with minimal dependencies. |
| Outcome: | The proposed framework outperforms teacher-trained models on multiple datasets and with a fixed model capacity. |
On Sparsifying Encoder Outputs in Sequence-to-Sequence Models (2021.findings-acl)
Copied to clipboard
| Challenge: | Using sequence-to-sequence models, encoder outputs are usually transferred to the decoder for generation, but in this study, encoded outputs can be compressed to shorten the sequence for decoding. |
| Approach: | They propose to use a stochastic gate-based algorithm to mask encoder outputs to shorten the sequence delivered for decoding. |
| Outcome: | The proposed model can be used to shorten encoder outputs to short a sequence . the proposed model yields a speedup of up to 1.65 on document summarization and 1.20 on character-based machine translation tasks. |
FrameNet-assisted Noun Compound Interpretation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for predicting semantic labels for noun compound interpretation are difficult. |
| Approach: | They propose to predict semantic labels in a continuous embedding space using FrameNet data. |
| Outcome: | The proposed method performs well on unseen labels, with 5% and 2% improvement over baselines for frame and FE prediction. |
Hypernym Discovery via a Recurrent Mapping Model (2021.findings-acl)
Copied to clipboard
| Challenge: | Empirical studies on SemEval-2018 Task 9 confirm the effectiveness of the presented model. |
| Approach: | They propose a parallel style model that maps query words to their hypernyms . they use a lexical-semantic relation to name a specific instance or subtype hyponym . |
| Outcome: | Empirical results on SemEval-2018 Task 9 confirm the effectiveness of the proposed model. |
Modeling the Influence of Verb Aspect on the Activation of Typical Event Locations with BERT (2021.findings-acl)
Copied to clipboard
| Challenge: | Prior studies have shown that aspect of the main verb plays an important role in non-core semantic roles such as locations. |
| Approach: | They tested the popular language model BERT to determine whether its predictions of prototypical locations were influenced by aspect. |
| Outcome: | The language model BERT modelled the typicality of locations independently of the verb aspect. |
On the Interaction of Belief Bias and Explanations (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to evaluate explainability fail to account for belief biases affecting human performance . previous studies have shown that neural models can make confident predictions relying on artifacts . |
| Approach: | They propose to account for belief bias in explainability by using models of varying quality and adversarial examples. |
| Outcome: | The proposed methods show that results change when using models of varying quality and adversarial examples. |
Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction (2021.findings-acl)
Copied to clipboard
| Challenge: | Bilingual Lexicon Induction (BLI) aims to map words in one language to their translations in another. |
| Approach: | They propose a mechanism to combine static word embeddings and contextual representations to utilize the advantages of both paradigms. |
| Outcome: | The proposed method improves performance on supervised and unsupervised BLI benchmarks on all language pairs by average improving 3.2 points over baselines. |
Exploring Unsupervised Pretraining Objectives for Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Unsupervised cross-lingual pretraining has significantly reduced the need for large parallel data. |
| Approach: | They compare unsupervised cross-lingual pretraining with masking and reconstructing inputs in the decoder to produce real sentences. |
| Outcome: | The proposed methods produce inputs resembling real (full) sentences, by reordering and replacing words based on their context. |
Knowledge-Grounded Dialogue Generation with Term-level De-noising (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for dialogue generation use terms to describe a post, such as 'question', 'utterance','source' and 'query', but this approach introduces noise and diminishes the effectiveness of the generative models. |
| Approach: | They propose a Knowledge Term Weighting Model that incorporates term-level de-noising of the selected knowledge into the model. |
| Outcome: | The proposed model achieves statistically significant improvements over methods without term weighting on two publicly available datasets Wizard of Wikipedia and Holl-E. |
Inspecting the concept knowledge graph encoded by modern language models (2021.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models are used to solve tasks such as summarization and information retrieval. |
| Approach: | They propose to use word embeddings, text generators, context encoders to extract underlying knowledge graphs of nine influential language models. |
| Outcome: | The proposed model is able to encode word embeddings, text generators, and context encoders, but suffers from several inaccuracies. |
Language Tags Matter for Zero-Shot Neural Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on multilingual machine translation have ignored the importance of LTs. |
| Approach: | They propose to use language tag (LT) strategies to indicate translation directions in MNMT to enhance consistency and alleviate off-target issues in zero-shot directions. |
| Outcome: | The proposed model could translate between unsupervised languages and achieve a +8 BLEU score difference over other LT strategies in translation tasks. |
Latent Reasoning for Low-Resource Question Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to multihop question generation require extensive data collection and decomposition. |
| Approach: | They propose a generative approach that optimizes the two-phase model without question decomposition data. |
| Outcome: | The proposed approach outperforms baselines on HOTPOTQA, a benchmark multi-hop question answering dataset. |
Probing Pre-Trained Language Models for Disease Knowledge (2021.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models perform medical reasoning tasks, but standard benchmarks lack examples that require such forms of reasoning. |
| Approach: | They propose a medical reasoning benchmark that uses pre-trained language models to analyze medical reasoning in the biomedical domain. |
| Outcome: | The proposed benchmarks are based on pre-trained language models that perform medical reasoning tasks. |
AugVic: Exploiting BiText Vicinity for Low-Resource NMT (2021.findings-acl)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) systems often exhibit poor performance due to the lack of large bitext training corpora in low-resource languages. |
| Approach: | They propose a data augmentation framework which exploits the vicinal samples of the given bitext without using extra monolingual data explicitly. |
| Outcome: | The proposed framework can diversify in-domain bitext data with finer level control on four low-resource language pairs. |
Provably Secure Generative Linguistic Steganography (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods of linguistic steganography generate high-security stegotext with statistical differences between the conditional probability distributions of stegot and natural text, which brings about security risks. |
| Approach: | They propose a method which embeds secret information by Adaptive Dynamic Grouping of tokens according to their probability given by an off-the-shelf language model. |
| Outcome: | The proposed method generates steganographic text with perfect security . it is based on three public corpora and proves its security based upon mathematical tests . |
Retrieval Enhanced Model for Commonsense Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing frameworks for commonsense generation are lacking for pre-trained models. |
| Approach: | They propose a framework that uses concept matching to retrieve prototype sentences and trainable sentence retriever to enhance pre-training and fine-tuning. |
| Outcome: | The proposed framework achieves state-of-the-art on the large-scale Common-Gen benchmark. |
Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent work on Text-to-SQL for multi-turn dialogue has attracted great interest . current approaches mostly employ end-to end models and face data sparsity problems . |
| Approach: | They propose a decoupled multi-turn text-to-SQL framework where dialogue context is explicitly solved by an utterance rewrite model and a single-turn Text-toSQl parser are proposed. |
| Outcome: | The proposed method outperforms existing models on SParC and CoSQL datasets without annotated in-domain data. |
Adjacency List Oriented Relational Fact Extraction via Adaptive Multi-task Learning (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models for relational fact extraction do not analyze the output data structure from the perspective of graph representation flexibility and heterogeneity. |
| Approach: | They propose a relational fact extraction model based on graph-oriented analytical perspective that outperforms other models. |
| Outcome: | The proposed model outperforms state-of-the-art models on two benchmark datasets and shows that it is flexible and space-efficient. |
Self-Supervised Document Similarity Ranking via Contextualized Language Models and Hierarchical Inference (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to document-to-document similarity ranking are limited to relatively short documents or lack similarity labels. |
| Approach: | They propose a self-supervised method for document similarity ranking that can be applied to documents of arbitrary length. |
| Outcome: | The proposed model outperforms existing methods on large documents datasets. |
How Good Is NLP? A Sober Look at NLP Tasks through the Lens of Social Impact (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent years have seen many breakthroughs in natural language processing (NLP), transitioning it from a mostly theoretical field to one with many real-world applications. |
| Approach: | They propose a moral philosophy definition of social good and a framework to evaluate the direct and indirect real-world impact of NLP tasks. |
| Outcome: | The proposed framework evaluates the direct and indirect real-world impact of NLP tasks and adopts the methodology of global priorities research to identify priority causes for NLP research. |
IgSEG: Image-guided Story Ending Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing tasks such as story ending generation generate text-based story endings, but visual storytelling generates photo-streams-based stories. |
| Approach: | They propose a task called Image-guided Story Ending Generation (IgSEG) given a multi-sentence story plot and an ending-related image, they propose MGCL to solve these challenges. |
| Outcome: | The proposed model outperforms baselines on automatic and human evaluation. |
Improve Query Focused Abstractive Summarization by Incorporating Answer Relevance (2021.findings-acl)
Copied to clipboard
| Challenge: | Query focused summarization models aim to generate summaries from source documents that can answer the given query. |
| Approach: | They propose a QFS-BART model that incorporates the explicit answer relevance of the source documents given the query via a question answering model. |
| Outcome: | Empirical results show that the proposed model achieves the new state-of-the-art performance. |
Learning a Reversible Embedding Mapping using Bi-Directional Manifold Alignment (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models that perform unidirectional mappings are unipolar and unintended . |
| Approach: | They propose a bi-directional mapping algorithm that learns a non-linear mapping between two manifolds by explicitly training it to be bijective. |
| Outcome: | The proposed model reduces the number of models by 50% and improves performance over unidirectional translation models. |
Probabilistic Graph Reasoning for Natural Proof Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to reasoning over formal representations do not explicitly consider inter-dependency between answers and proofs. |
| Approach: | They propose a novel approach for joint answer prediction and proof generation using an induced graphical model. |
| Outcome: | The proposed approach achieves 10%-30% improvement on QA accuracy in evaluations under diverse conditions. |
Enhancing Zero-shot and Few-shot Stance Detection with Commonsense Knowledge Graph (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for stance detection are not applicable to zero-shot and few-shot scenarios. |
| Approach: | They propose a model that integrates commonsense knowledge into a stance detection model. |
| Outcome: | The proposed model outperforms state-of-the-art methods on zero-shot and few-shot stance detection tasks. |
Dialogue Graph Modeling for Conversational Machine Reading (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for conversational machine reading (CMR) are not effective for capturing multiple objects in complex interactive scenarios. |
| Approach: | They propose a dialogue graph modeling framework that captures explicit and implicit interactions hidden in the rule documents and a model that asks clarification questions to the machine. |
| Outcome: | The proposed model exceeds the milestone accuracy score of 80% on the ShARC benchmark and achieves new state-of-the-art by first exceeding the milestone precision score of 90%. |
IndoCollex: A Testbed for Morphological Transformation of Indonesian Colloquial Words (2021.findings-acl)
Copied to clipboard
Haryo Akbarianto Wibowo, Made Nindyatama Nityasya, Afra Feyza Akyürek, Suci Fitriany, Alham Fikri Aji, Radityo Eko Prasojo, Derry Tanti Wijaya
| Challenge: | Existing research on word normalization in Indonesian language relies on static dictionaries and machine translation. |
| Approach: | They propose to use Twitter to annotate Indonesian colloquial words with their standard forms and their word formation types/tags to perform morphological word normalization. |
| Outcome: | The proposed dataset analyzes morphological word normalization on Indonesian colloquial Lexicons and provides a baseline for future work. |
Manifold Adversarial Augmentation for Neural Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent studies show that NMT models can drop significantly when small perturbations are added to input sentences. |
| Approach: | They propose a data augmentation approach to sample sentences from the vicinity distributions in higher-level representations. |
| Outcome: | The proposed method improves translation accuracy on training samples from higher-level representations. |
Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing few-shot learning methods learn a single task each time with a few examples . but, real-world applications often contain multiple closely related tasks . |
| Approach: | They propose a few-shot joint learning scheme that captures intent and slot relationships from only a handful of examples and adapts the bridged metric space to specific few- shot domain. |
| Outcome: | The proposed model outperforms baseline models on two public datasets on intent and slot . the proposed model significantly outperformed baseline models in one and five shots settings. |
Insertion-based Tree Decoding (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing non-autoregressive decoders that are sub-linear can speed up inference for longer sequences. |
| Approach: | They propose a sub-linear nonautoregressive tree decoder that uses tree-based insertion operations to generate trees in sub-lines . they evaluate their approach on semantic parsing and compare it against strong baselines . |
| Outcome: | The proposed approach achieves competitive accuracies while reducing the number of decoding steps. |
Is the Lottery Fair? Evaluating Winning Tickets Across Demographics (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent studies suggest weight pruning compromises fairness of machine learning models . however, no empirical evaluation has been done in the context of natural language processing. |
| Approach: | They evaluate the fairness of lottery ticket extraction through layer-wise and global weight pruning across three languages and two tasks. |
| Outcome: | The proposed model is compared with two text classification datasets annotated with demographic information. |
SSMix: Saliency-Based Span Mixup for Text Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | SSMix synthesizes a sentence while preserving the locality of two original texts by span-based mixing and keeping more tokens related to the prediction relying on saliency information. |
| Approach: | They propose a new method where the operation is performed on input text rather than on hidden vectors like previous approaches. |
| Outcome: | The proposed method outperforms hidden-level mixup methods on a wide range of text classification benchmarks including textual entailment, sentiment classification, and questiontype classification. |
Detecting Bot-Generated Text by Characterizing Linguistic Accommodation in Human-Bot Interactions (2021.findings-acl)
Copied to clipboard
| Challenge: | Language generation models' democratization makes it easier to generate human-like text at-scale for nefarious activities, from spreading misinformation to targeting specific groups with hate speech. |
| Approach: | They propose to use linguistic alignment to detect bot-generated text rather than using it directly. |
| Outcome: | The proposed methods are more robust across datasets and models if they use information about how people respond to it rather than using the bot's text directly. |
Defending Pre-trained Language Models from Adversarial Word Substitution Without Performance Sacrifice (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing defense approaches suffer from notable performance loss and complexities. |
| Approach: | They propose a framework for detecting anomalies with frequency-aware randomization to defend adversarial word substitution. |
| Outcome: | The proposed framework outperforms existing defense methods over various tasks with much higher inference speed. |
BERT-Proof Syntactic Structures: Investigating Errors in Discontinuous Constituency Parsing (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent results show that pretrained language models can be used for many tasks with high accuracy and high performance. |
| Approach: | They propose two methods for automatically analysing discontinuous parsers' errors. |
| Outcome: | The proposed methods characterize errors of a state-of-the-art transition-based discontinuous parser and provide an overview of the contribution of BERT to this task. |
DoT: An efficient Double Transformer for NLP tasks with tables (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have shown that transformer-based approaches to NLP tasks are slow and require computational and memory costs. |
| Approach: | They propose a transformer-based model that decomposes a problem into two sub-tasks and a pruning transformer that takes as input the pruning scores. |
| Outcome: | The proposed model improves training and inference time by at least 50% for a small drop in accuracy and also enables the model to maintain similar accuracy as slower baseline models. |
Grammatical Error Correction as GAN-like Sequence Labeling (2021.findings-acl)
Copied to clipboard
| Challenge: | Traditional GEC models learn from sentences with fixed error rates . sequence labeling approaches suffer from a couple of key problems . |
| Approach: | They propose a GAN-like sequence labeling model with a grammatical error detector and a generator to correct grammamatical errors. |
| Outcome: | The proposed model improves the state-of-the-art in GEC and improves on benchmarks. |
Neural Entity Recognition with Gazetteer based Fusion (2021.findings-acl)
Copied to clipboard
| Challenge: | Named entity recognition systems can be applied to clinical domains where only limited data is accessible and interpretability is important. |
| Approach: | They propose to use auxiliary gazetteer model to fuse it with NER system . this allows for better robustness and interpretability across different clinical datasets . |
| Outcome: | The proposed model is data efficient and can adapt to new mentions in gazetteers without retraining. |
Hyperbolic Temporal Knowledge Graph Embeddings with Relational and Time Curvatures (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge Graph models for Link Prediction are insensitive to time. |
| Approach: | They propose a time-aware extension of ATTH model which defines curvature of a Riemannian manifold as the product of both relation and time. |
| Outcome: | The proposed model can achieve competitive or even better performance than the state-of-the-art model on Temporal KGs, albeit its nontemporality. |
Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering (2021.findings-acl)
Copied to clipboard
| Challenge: | Disfluencies are an under-studied topic in NLP, even though it is ubiquitous in human conversation. |
| Approach: | They propose a challenge question answering dataset where humans introduce contextual disfluencies in previously fluent questions. |
| Outcome: | The proposed dataset shows that existing models degrade significantly when tested on DISFL-QA in a zero-shot setting. |
Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to reduce disparities in model outcomes have focused on data augmentation, debiasing model embeddings, or adding fairness-based optimization objectives during training. |
| Approach: | They propose to use certified word substitution robustness methods to improve equality of odds and equality of opportunity on multiple text classification tasks. |
| Outcome: | The proposed methods improve equality of odds and equality of opportunity on multiple text classification tasks. |
A Joint Model for Structure-based News Genre Classification with Application to Text Summarization (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models for structure-based news genre classification identify news structure types and news elements . authors show that the model outperforms variants that perform two tasks independently . |
| Approach: | They propose a joint model that identifies one of four commonly used news structures for a news article and recognizes a sequence of news elements within the article that define the corresponding news structure. |
| Outcome: | The proposed model outperforms variants that perform two tasks independently . it predicts news structure type and news elements and improves text summarization . |
Representing Syntax and Composition with Geometric Transformations (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models of word meaning are based on syntactic rather than proximal co-occurrences, but they are not suitable for syntax sensitive composition. |
| Approach: | They propose to encode syntactic structure by extending the Skip-Gram with Negative sampling architecture from word2vec. |
| Outcome: | The proposed models perform favourably on benchmark word similarity tasks on similarity tests on similar words compared to models based on proximal co-occurrence . however, the real promise of distributional models is the potential for syntax-sensitive composition. |
Figurative Language in Recognizing Textual Entailment (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing RTE models struggle to capture figurative language, despite its ubiquity, it remains a bottleneck in automatic text understanding. |
| Approach: | They propose to frame five existing figurative language datasets into over 12,500 RTE examples. |
| Outcome: | The proposed models struggle to perform pragmatic inference and reasoning about world knowledge. |
To Point or Not to Point: Understanding How Abstractive Summarizers Paraphrase Text (2021.findings-acl)
Copied to clipboard
| Challenge: | Abstractive summarization models have seen great improvements in recent years, but there is limited understanding of the strategies different models employ and how they relate their understanding of language. |
| Approach: | They characterize how one popular abstractive model uses an explicit copy/generation switch to control its level of abstraction vs extraction . they find that abstractive summarization models lack the semantic understanding necessary to generate paraphrases that are both abstractive and faithful to the source document. |
| Outcome: | The proposed model uses syntactic boundaries to truncate sentences that are often copied verbatim. |
AgreeSum: Agreement-Oriented Multi-Document Summarization (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on agreement-oriented multidocument summarization have focused on clusters of articles . a recent study focused on the use of a pretraining framework to summarize articles based on the "union" of the articles. |
| Approach: | They propose to use agreement-oriented multidocument summarization to provide agreement-orientated summaries that represent information common to all articles. |
| Outcome: | The proposed task is called agreement-oriented multidocument summarization . the authors apply the pretrained model PEGASUS onto the task . |
BERT Busters: Outlier Dimensions that Disrupt Transformers (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies show that pre-trained Transformers are remarkably robust to pruning. |
| Approach: | They show that pre-trained Transformer encoders are surprisingly fragile to pruning . they show that disabling them significantly degrades both the MLM loss and the downstream task performance. |
| Outcome: | The results show that the removal of features in pre-trained transformers significantly degrades both the MLM loss and the downstream task performance. |
“We will Reduce Taxes” - Identifying Election Pledges with Language Models (2021.findings-acl)
Copied to clipboard
| Challenge: | a political party's manifestos are published before any election, but do they follow through? a new study uses neural models to distinguish between actual pledges and general statements . |
| Approach: | They use election manifestos of Swedish and Indian political parties to learn neural models that distinguish actual pledges from generic positions. |
| Outcome: | The proposed model can predict election year and manifesto's party, while context introduces noise. |
WeaQA: Weak Supervision via Captions for Visual Question Answering (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for training visual question answering models rely on datasets with human-annotated image-quest-answer triplets. |
| Approach: | They propose a method to train models with synthetic Q-A pairs generated procedurally from captions. |
| Outcome: | The proposed method trains models with synthetic Q-A pairs generated from captions on three VQA benchmarks. |
How well do you know your summarization datasets? (2021.findings-acl)
Copied to clipboard
| Challenge: | State-of-the-art summarization systems are trained on massive datasets scraped from the web. |
| Approach: | They manually analyse 600 samples from three popular summarization datasets . they use a six-class typology which captures different noise types and degrees of summarizing difficulty. |
| Outcome: | The proposed model performs better on large datasets than on the current models. |
Multilingual Translation from Denoising Pre-Training (2021.findings-acl)
Copied to clipboard
Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan
| Challenge: | Recent work shows potential of training one model for multilingual machine translation . but little has been explored on the potential to combine denoising pretraining with multilingual translation in a single model. |
| Approach: | They propose to combine denoising pretraining with multilingual machine translation in a single model. |
| Outcome: | The proposed model improves over models trained from scratch and bilingually for translation into English. |
Annotations Matter: Leveraging Multi-task Learning to Parse UD and SUD (2021.findings-acl)
Copied to clipboard
| Challenge: | Multi-task learning (MTL) has shown promise in various NLP tasks such as semantic dependency parsing. |
| Approach: | They propose to use two parallel treebanks to improve parsing performance. |
| Outcome: | The proposed model is based on two parallel treebanks with similar annotation schemes but differing in linguistic annotation preferences. |
Generating Informative Conclusions for Argumentative Texts (2021.findings-acl)
Copied to clipboard
| Challenge: | Argumentative texts often omit explicit conclusions, expecting readers to infer them rather . a corpus of 136,996 arguments is compiled and used to generate informative conclusions . |
| Approach: | They propose to generate informative conclusions from a large-scale corpus of argumentative texts . they propose to use argumentative knowledge to augment the corpus and refine the model . |
| Outcome: | The proposed corpus of argumentative texts and their conclusions is compiled and analyzed . the results show that the proposed model is informative and concise . |
Substructure Substitution: Structured Data Augmentation for NLP (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing work focuses on word-level manipulation or global sequence-to-sequence style generation. |
| Approach: | They propose a family of data augmentation methods that generalize prior methods by substituting substructures with others having the same label. |
| Outcome: | The proposed methods can be applied to many structured NLP tasks such as part-of-speech tagging and parsing. |
Towards Protecting Vital Healthcare Programs by Extracting Actionable Knowledge from Policy (2021.findings-acl)
Copied to clipboard
Vanessa Lopez, Nagesh Yadav, Gabriele Picco, Inge Vejsbjerg, Eoin Carrol, Seamus Brady, Marco Luca Sbodio, Lam Thanh Hoang, Miao Wei, John Segrave
| Challenge: | In the U.S., an estimated annual amount of USD$20-30B is lost to Fraud, Waste and abuse (FWA) |
| Approach: | They propose a method for automatically extracting knowledge from healthcare policy documents into a semantically-meaningful knowledge graph of rules. |
| Outcome: | The proposed method fuses advances in dependency parsing with a policy ontology to transform the content of regulatory healthcare policy into human-friendly policy rules with human oversight. |
Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing kNN-based augmentation techniques blindly incorporate all samples, but MiniMax-kNN uses a subset of augmented samples to maximize KL-divergence between teacher and student models. |
| Approach: | They propose a semi-supervised approach to augmented data augmentation using kNN. |
| Outcome: | The proposed method outperforms existing kNN-based augmentation techniques on several classification tasks and requires fewer augmented examples and less computation to achieve superior performance. |
It’s All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning (2021.findings-acl)
Copied to clipboard
| Challenge: | gilbert et al.: commonsense reasoning is a key problem in natural language processing but its capabilities are still unstudied. gilland eetal.: a new approach to commonsensible reasoning is needed to solve the problem. |
| Approach: | They propose a method which trains a linear classifier with weights of multi-head attention as features and a multilingual Winograd Schema corpus to measure cross-lingual generalization ability. |
| Outcome: | The proposed approach performs competitively with recent approaches even when applied to other languages in a zero-shot manner. |
Biomedical Interpretable Entity Representations (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing work on general interpretable representation learning does not transfer to biomedicine . pre-trained models induce dense entity representations but are not immediately interpretable. |
| Approach: | They propose a method that exploits BIER's final sparse and intermediate dense representations to facilitate model and entity type debugging. |
| Outcome: | The proposed model performs well on biomedical tasks including disambiguation and label classification. |
Learning Robust Latent Representations for Controllable Speech Synthesis (2021.findings-acl)
Copied to clipboard
| Challenge: | Variational Auto-Encoders (VAEs) for learning disentangled latent representations in speech fail to learn latent clusters of speaker attributes when trained on limited or noisy datasets. |
| Approach: | They propose a Variational Auto-Encoder (VAE) that minimizes mutual information between latent variables and learns controllable latent representations in speech data. |
| Outcome: | The proposed model reduces the cluster overlap of speaker attributes by 30% over LSTM-VAE. |
How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for subword splitting penalize the representation of feminine linguistic markings. |
| Approach: | They propose a method that preserves subword splitting while leveraging character-based segmentation to properly translate gender. |
| Outcome: | The proposed approach preserves BPE overall translation quality while leveraging the higher ability of character-based segmentation to properly translate gender. |
On the Ethical Limits of Natural Language Processing on Legal Text (2021.findings-acl)
Copied to clipboard
| Challenge: | Legal NLP holds the promise of improving access to justice and offers tools for empirical analysis of law on a large scale. |
| Approach: | They propose ways to think systematically about ethical limits of NLP . they place emphasis on three crucial normative parameters that have been underestimated . |
| Outcome: | The proposed methods are based on a real-life scenario that has prompted debate in the legal NLP community. |
An Exploratory Analysis of the Relation between Offensive Language and Mental Health (2021.findings-acl)
Copied to clipboard
| Challenge: | Using computational models, the use of offensive language is pervasive in social media . a popular line of research is the study of machine learning classifiers to identify offensive content online . |
| Approach: | They analyze social media posts written by individuals with depression and those without . they train computational models to compare use of offensive language with depression detection . |
| Outcome: | The proposed models show that offensive language is more frequently used in the samples written by individuals with depression and those showing signs of depression. |
Transforming Term Extraction: Transformer-Based Approaches to Multilingual Term Extraction Across Domains (2021.findings-acl)
Copied to clipboard
| Challenge: | Automated Term Extraction (ATE) is a challenging task, with few exceptions. |
| Approach: | They propose to use a transformer-based term extraction model to extract terms from sentences . they also propose to employ a language model for token classification and a sequence model to reduce sentences to terms . |
| Outcome: | The proposed models outperform baselines on the ATE challenge TermEval 2020 dataset in English, French, and Dutch. |
ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent work shows that transformers can generate both implications of a theory and the natural language proofs that support them. |
| Approach: | They propose a generative model that generates both implications of a theory and natural language proofs that support them. |
| Outcome: | The proposed model generates both implications of a theory and the natural language proofs that support them. |
Probing Image-Language Transformers for Verb Understanding (2021.findings-acl)
Copied to clipboard
| Challenge: | Multimodal image-language transformers have achieved impressive results on a variety of tasks that rely on fine-tuning. |
| Approach: | They collect a dataset of image-sentence pairs consisting of 421 verbs . they evaluate pretrained image-language transformers and find they fail more in situations that require verb understanding compared to other parts of speech. |
| Outcome: | The proposed model trains on a manually-annotated and smaller dataset does better on the task. |
Implications of Using Internet Sting Corpora to Approximate Underage Victims (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing systems for classification and triaging child exploitation cases require a high quality of data. |
| Approach: | They propose to annotate a corpus of underage victim chats with convicted predators to compare their goals and tactics. |
| Outcome: | The proposed model is based on a corpus of victim, vigilante, and LEO conversations with convicted predators. |
Detecting Domain Polarity-Changes of Words in a Sentiment Lexicon (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on sentiment lexicons have focused on domain-dependent sentiment words. |
| Approach: | They propose a graph-based technique to detect and correct domain-dependent sentiment words . they propose to use a sentiment lexicon to classify sentiments in a lexical-based classifier . |
| Outcome: | The proposed method is effective on multiple datasets from different domains. |
Analyzing Online Political Advertisements (2021.findings-acl)
Copied to clipboard
| Challenge: | Online political advertising is an integral part of modern digital election campaigning. |
| Approach: | They propose to use textual and visual information from pre-trained neural models to infer the political ideology of an ad sponsor and identify whether the sponsor is an official political party or a third-party organization. |
| Outcome: | The proposed approach outperforms state-of-the-art methods for generic commercial ad classification and linguistic analysis to study the characteristics of political ads discourse. |
Do Language Models Perform Generalizable Commonsense Inference? (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent work has applied pretrained language models to populate commonsense knowledge graphs (CKGs) but there is a lack of understanding on their generalization to multiple CKGs, unseen relations, and novel entities. |
| Approach: | They analyze the ability of pretrained language models to perform generalizable commonsense inference in terms of knowledge capacity, transferability and induction. |
| Outcome: | The proposed models can adapt to different schemas defined by multiple CKGs but fail to generalize to new relations. |
Probing Multi-modal Machine Translation with Pre-trained Language Model (2021.findings-acl)
Copied to clipboard
| Challenge: | Multi-modal machine translation (MMT) aimed at using images to help disambiguate the target during translation but recent studies showed that visual features are either negligible or incremental. |
| Approach: | They propose to incorporate a visual language model on the source side to improve multi-modal translation quality significantly. |
| Outcome: | The proposed model improves the translation quality significantly on the multi-modal dataset. |
The interplay between language similarity and script on a novel multi-layer Algerian dialect corpus (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have focused on cross-lingual transfer between languages with similar typology and languages of different scripts. |
| Approach: | They propose to annotate Algerian user-generated comments with parallel annotations . they also investigate the effect of script vs. language similarity in cross-lingual transfer . |
| Outcome: | The proposed model fine-tunes multi-lingual models on Algerian language and scripts . it shows that script vs. language similarity is important for part-of-speech tagging and sentiment analysis . |
Few-Shot Upsampling for Protest Size Detection (2021.findings-acl)
Copied to clipboard
| Challenge: | a common task in social science is "upsampling" coarse document labels to finegrained labels . a new task is proposed for "up-samping" coarse labels to more detailed information . |
| Approach: | They propose a task for "upsampling" coarse document labels to finegrained labels or spans . they use a question answering format to provide fine-grained label information . |
| Outcome: | The proposed method outperforms a pre-trained model on a small set of examples but is weaker on fewer examples. |
Modeling the Unigram Distribution (2021.findings-acl)
Copied to clipboard
| Challenge: | a novel model for estimating the unigram distribution is proposed for a language . the model is based on the word type and word type distributions, but does not consider contextual information. |
| Approach: | They propose a neuralization of Goldwater's (2011) model for estimating the unigram distribution in a language. |
| Outcome: | The proposed model outperforms character-level models in estimating the unigram distribution in a language. |
On the Lack of Robust Interpretability of Neural Text Classifiers (2021.findings-acl)
Copied to clipboard
Muhammad Bilal Zafar, Michele Donini, Dylan Slack, Cedric Archambeau, Sanjiv Das, Krishnaram Kenthapadi
| Challenge: | Several models have been proposed to interpret models with feature-based interpretability methods. |
| Approach: | They propose to quantify the robustness of neural text classifiers by using two randomization tests to compare models with identical initializations. |
| Outcome: | The proposed methods show surprising deviations from expected behavior . the results raise questions about the extent of insights that practitioners may draw from interpretations. |
Multimodal Graph-based Transformer Framework for Biomedical Relation Extraction (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models based on textual data do not capture context beyond the sentence. |
| Approach: | They propose a framework that enables the model to learn multi-omnics biological information about entities (proteins) with the help of additional multi-modal cues like molecular structure. |
| Outcome: | The proposed model is generalized and optimized for protein-protein interaction task and benefited from additional domain-specific cues. |
Summary Grounded Conversation Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing datasets for conversation summarization are small due to the lack of large-scale datasets. |
| Approach: | They propose three approaches to generate summary grounded conversations, and evaluate the generated conversations using automatic measures and human judgements. |
| Outcome: | The proposed models can generate entire conversations with only a summary of a conversation as the input. |
A Non-Autoregressive Edit-Based Approach to Controllable Text Simplification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models that generate generic simplified outputs for a given source text have been used to specify output properties. |
| Approach: | They propose a non-autoregressive model that iteratively edits an input sequence and incorporates lexical complexity information into the refinement process to generate simplifications that better match the desired output complexity. |
| Outcome: | The proposed model incorporates lexical complexity information into the refinement process to achieve more complex simplification operations such as content deletion and paraphrasing, as well as sentence splitting. |
Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference (2021.findings-acl)
Copied to clipboard
| Challenge: | Multilingual transformers have been shown to have remarkable transfer skills in zero-shot settings. |
| Approach: | They investigate cross-lingual transfer abilities of XLM-R for Chinese and English natural language inference using a large scale Chinese dataset. |
| Outcome: | The proposed model trains on Chinese and English natural language inference datasets. |
Using surprisal and fMRI to map the neural bases of broad and local contextual prediction during natural language comprehension (2021.findings-acl)
Copied to clipboard
| Challenge: | a prior work using surprisal only considered within-sentence context, using n-grams, neural language models, or syntactic structure as conditioning context. |
| Approach: | They extend the surprisal approach to use broader topical context . they identify distinct patterns of neural activation for lexical surprised and topical surpresed . |
| Outcome: | The proposed method captures effects of local and topical contexts on processing . it shows that local and broad contextual cues recruit different brain regions . |
Assessing the Syntactic Capabilities of Transformer-based Multilingual Language Models (2021.findings-acl)
Copied to clipboard
| Challenge: | Multilingual Transformer-based language models have been shown to be excellent learners in crosslingual transfer tasks. |
| Approach: | They evaluate the syntactic generalization capabilities of BERT and RoBERTa models on English and Spanish tests. |
| Outcome: | The proposed models perform well on English and Spanish tests, and the proposed tests are compared against models on the same language and models on two different languages. |
Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level (2021.findings-acl)
Copied to clipboard
| Challenge: | Larger models have higher out-of-distribution robustness, while smaller models have lower accuracy on rare subgroups. |
| Approach: | They develop statistically rigorous methods to investigate whether large models are better on every instance . they find that individual predictions are highly sensitive to noise in the randomness in training . |
| Outcome: | The proposed model is worse than BERT-MINI on 1-4% of instances across MNLI, SST-2, and QQP, compared to the overall accuracy improvement of 2-10%. |
Named Entity Recognition through Deep Representation Learning and Weak Supervision (2021.findings-acl)
Copied to clipboard
| Challenge: | Weakly supervised named entity recognition (NER) uses noisy labels to estimate the true labels of a dataset. |
| Approach: | They propose a model to learn optimal assignments of latent NER tags using observed tokens and weak labels provided by labeling functions. |
| Outcome: | The proposed model improves the quality of weak labels on four public datasets. |
Explaining NLP Models via Minimal Contrastive Editing (MiCE) (2021.findings-acl)
Copied to clipboard
| Challenge: | Cognitive science and philosophy research has shown that human explanations are contrastive . a contrast case plays a key role in modulating what explanations can be given . |
| Approach: | They propose a method for producing contrastive explanations of model predictions . they edit models' outputs to change model outputs, and then edit them to the contrast case . |
| Outcome: | a new method produces contrastive explanations of model predictions in the form of edits . the edits are minimal and fluent, consistent with human contrastive edits. |
Differential Privacy for Text Analytics via Natural Text Sanitization (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing text sanitization mechanisms provide low utility, as cursed by the high-dimensional text representation. |
| Approach: | They propose to use sanitized texts to samaritize training data . they propose to retrain and fine-tune the senitization-aware language model . |
| Outcome: | The proposed approach enables privacypreserving natural language processing over the BERT language model with promising utility. |
Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation (2021.findings-acl)
Copied to clipboard
| Challenge: | Open-domain neural dialogue models have achieved high performance in response ranking and evaluation tasks. |
| Approach: | They propose methods for automatically creating adversarial negative training data . they use mask-and-fill and keyword-guided approaches to generate negative examples . |
| Outcome: | The proposed approaches outperform baseline models in providing informative negative examples for training dialogue systems. |
Leveraging Abstract Meaning Representation for Knowledge Base Question Answering (2021.findings-acl)
Copied to clipboard
Pavan Kapanipathi, Ibrahim Abdelaziz, Srinivas Ravishankar, Salim Roukos, Alexander Gray, Ramón Fernandez Astudillo, Maria Chang, Cristina Cornelio, Saswati Dana, Achille Fokoue, Dinesh Garg, Alfio Gliozzo, Sairam Gurajada, Hima Karanam, Naweed Khan, Dinesh Khandelwal, Young-Suk Lee, Yunyao Li, Francois Luus, Ndivhuwo Makondo, Nandana Mihindukulasooriya, Tahira Naseem, Sumit Neelam, Lucian Popa, Revanth Gangi Reddy, Ryan Riegel, Gaetano Rossiello, Udit Sharma, G P Shrivatsa Bhargav, Mo Yu
| Challenge: | Existing approaches face challenges including complex question understanding and lack of large end-to-end training datasets. |
| Approach: | They propose a modular knowledge base question answering system that leverages AMR parses for task-independent question understanding. |
| Outcome: | The proposed system achieves state-of-the-art performance on two prominent KBQA datasets based on DBpedia. |
On the Gap between Adoption and Understanding in NLP (2021.findings-acl)
Copied to clipboard
| Challenge: | a recent paper argues that current publications foster a gap between adoption and understanding of models . it also makes it easier to meet publication demands with method papers, argues the paper . |
| Approach: | They argue that current NLP publication models foster a gap between adoption and understanding of models . they argue that everlarger models make it harder to explain how our methods work . |
| Outcome: | The authors argue that current publications foster a gap between adoption and understanding of models . they argue that the rise of everlarger models makes it harder to explain how our methods work . |
Learning Disentangled Latent Topics for Twitter Rumour Veracity Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to rumour veracity classification relied on feature engineering. |
| Approach: | They propose a model which disentangles the informational content of a tweet from the manner in which it is written. |
| Outcome: | The proposed model disentangles the informational content of a tweet from the manner in which the information is written. |
Perceptual Models of Machine-Edited Text (2021.findings-acl)
Copied to clipboard
| Challenge: | a dataset of human judgments of machine-edited text is presented . we compare six different methods to create generic models of human perception . |
| Approach: | They propose to use six machine-editing methods to model human perceptions of edited text . they use a dataset of human judgments of machine-edited text and scientific abstracts . |
| Outcome: | The proposed model is based on human judgments of machine-edited text and scientific abstracts . human judgment of edited text is predicted to be within 6% of human consensus labeling . |
Scaling Within Document Coreference to Long Texts (2021.findings-acl)
Copied to clipboard
Raghuveer Thirukovalluru, Nicholas Monath, Kumar Shridhar, Manzil Zaheer, Mrinmaya Sachan, Andrew McCallum
| Challenge: | Existing end-to-end coreference resolution models use expensive span representations and antecedent prediction mechanisms. |
| Approach: | They propose an approximation to end-to-end coreference resolution models which scales gracefully to documents of any length. |
| Outcome: | The proposed model reduces training and inference time and memory costs compared to current models with minimal loss in accuracy. |
LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent work on text style transfer proposes single-span editing as an alternative to generating the target text from scratch. |
| Approach: | They propose a coarse-to-fine editor for style transfer that transforms text using Levenshtein edit operations (e.g. insert, replace, delete). |
| Outcome: | The proposed method outperforms existing methods on sentiment and politeness transfer and improves model performance. |
Constructing Flow Graphs from Procedural Cybersecurity Texts (2021.findings-acl)
Copied to clipboard
| Challenge: | Graph Convolution Network with BERT sentence embeddings outperforms BERT in all three domains. |
| Approach: | They propose to identify relevant information from procedural texts and generate information flows between sentences from them. |
| Outcome: | The proposed method outperforms BERT in two domains of cybersecurity. |
Cluster-Former: Clustering-based Sparse Transformer for Question Answering (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models for encoding long sequences in deep learning suffer from high latency and memory demands. |
| Approach: | They propose a clustering-based sparse Transformer framework to perform attention across chunked sequences. |
| Outcome: | The proposed framework achieves state-of-the-art on several major QA benchmarks. |
Minimally-Supervised Morphological Segmentation using Adaptor Grammars with Linguistic Priors (2021.findings-acl)
Copied to clipboard
Ramy Eskander, Cass Lowry, Sujay Khandagale, Francesca Callejas, Judith Klavans, Maria Polinsky, Smaranda Muresan
| Challenge: | Unsupervised morphological segmentation is an essential subtask in many natural language processing applications. |
| Approach: | They introduce two types of priors: grammar definition and linguist-provided affixes . they show that priors boost morphological segmentation performance in a minimally-supervised manner . |
| Outcome: | The proposed priors achieve 8.9% and 34.2% error reductions over the state-of-the-art unsupervised system. |
Multi-Task Learning and Adapted Knowledge Models for Emotion-Cause Extraction (2021.findings-acl)
Copied to clipboard
Elsbeth Turcan, Shuai Wang, Rishita Anubhai, Kasturi Bhattacharjee, Yaser Al-Onaizan, Smaranda Muresan
| Challenge: | Detecting what emotions are expressed in text is a well-studied problem in natural language processing. |
| Approach: | They propose methods that combine common-sense knowledge with multi-task learning to perform joint emotion classification and emotion cause tagging. |
| Outcome: | The proposed models improve on both tasks when using common-sense reasoning and a multitask framework. |
The Utility and Interplay of Gazetteers and Entity Segmentation for Named Entity Recognition in English (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent papers introduce methods to incorporate gazetteer features and entity segmentation techniques in neural named entity recognition models. |
| Approach: | They propose to integrate gazetteer features and entity segmentation techniques into neural named entity recognition models. |
| Outcome: | The proposed methods improve entity segmentation and not just entity typing. |
On the Cost-Effectiveness of Stacking of Neural and Non-Neural Methods for Text Classification: Scenarios and Performance Prediction (2021.findings-acl)
Copied to clipboard
| Challenge: | Neural network algorithms excel on Automatic Text Classification tasks, but they are expensive and require high computational costs. |
| Approach: | They propose to exploit the cost-effectiveness of stacking of automatic text classification classifiers to improve their effectiveness. |
| Outcome: | The proposed method can predict the best ensemble in each scenario using only fraction of available training data. |
Unsupervised Domain Adaptation for Event Detection using Domain-specific Adapters (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to ED are limited due to complexity of textual data and domain shift problem. |
| Approach: | They propose to use domain adapter-based Adaptation framework to improve event detection across domains. |
| Outcome: | The proposed framework significantly boosts the performance on target domains. |
Predicting in-hospital mortality by combining clinical notes with time-series data (2021.findings-acl)
Copied to clipboard
| Challenge: | In intensive care units, patient health is monitored through vital signals and clinical notes . previous work focused on predicting patient health using time-series data gathered from medical devices . |
| Approach: | They propose a model that combines clinical notes and vital data to make accurate mortality predictions. |
| Outcome: | The proposed model achieves an AUC score of 0.9, compared to the previous 0.87 . it can be used to make accurate in-hospital mortality predictions . |
Sequence Models for Computational Etymology of Borrowings (2021.findings-acl)
Copied to clipboard
| Challenge: | a computational model of word borrowing can be useful for lexicon expansion and language preservation. |
| Approach: | They propose to use neural sequence models to model word borrowings from a donor word to an incorporated word. |
| Outcome: | The proposed model beats baseline models in both directions, with the quantity of data strongly influencing performance. |
Learning Contextualized Knowledge Structures for Commonsense Reasoning (2021.findings-acl)
Copied to clipboard
Jun Yan, Mrigank Raman, Aaron Chan, Tianyu Zhang, Ryan Rossi, Handong Zhao, Sungchul Kim, Nedim Lipka, Xiang Ren
| Challenge: | Recent knowledge graph (KG) augmented models have achieved notable success on commonsense reasoning tasks. |
| Approach: | They propose a KG-augmented model that contextualizes extracted and generated knowledge by reasoning over both within a single graph structure. |
| Outcome: | The proposed model outperforms existing models on four commonsense reasoning benchmarks and a user study on edge validness and helpfulness. |
Analyzing Stereotypes in Generative Text Inference Tasks (2021.findings-acl)
Copied to clipboard
| Challenge: | Social psychology studies how social stereotypes are shared as part of cultural knowledge . |
| Approach: | They study how stereotypes manifest when potential targets are situated in neutral contexts . they collect human judgments on the presence of stereotypes in generated inferences based on annotator positionality . |
| Outcome: | The results show that the annotators' positions differ depending on the type of inferences they generate . |
HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to extract information graphs are difficult to scale to datasets with longer input texts because of their secondorder space/time complexities. |
| Approach: | They propose a Hybrid SPan GenerAtor that invertibly maps the information graph to an alternating sequence of nodes and edge types and generates them via a hybrid span decoder. |
| Outcome: | The proposed method outperforms state-of-the-art methods on the ACE05 dataset. |
Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation (2021.findings-acl)
Copied to clipboard
| Challenge: | Prior work has shown that having multiple valid references is important for automated evaluations. |
| Approach: | They propose a technique for automatically expanding a human generated reference to a set of candidate references. |
| Outcome: | The proposed method improves correlations between human-generated metrics and human ratings of system outputs. |
Who Blames or Endorses Whom? Entity-to-Entity Directed Sentiment Extraction in News Text (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for sentiment analysis do not consider direction of sentiments between political entities. |
| Approach: | They propose a novel task of identifying directed sentiment relationship between political entities from a given news document. |
| Outcome: | The proposed method is useful for social science research questions in the 2016 election and COVID-19. |
New Dataset and Strong Baselines for the Grammatical Error Correction of Russian (2021.findings-acl)
Copied to clipboard
| Challenge: | a new resource is created to evaluate grammatical error correction models in English . a subset of the dataset is annotated in Russian, which is hard to come by and expensive to annotate . |
| Approach: | They develop an annotated learner corpus of Russian extracted from the Lang-8 website. |
| Outcome: | The proposed dataset is compared against two state-of-the-art grammatical error correction models . the results show that the created corpus is more diverse than the existing one . |
A Formidable Ability: Detecting Adjectival Extremeness with DSMs (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on distributional semantic models capture abstract semantic properties across domains . abstract properties can form the basis for abstract semantic classes . |
| Approach: | They propose to use distributional semantic models to capture cross-domain properties . they use extremeness to model emergence of intensifier meaning in adverbs . |
| Outcome: | The proposed model can capture extremeness and intensifier meaning in adverbs. |
Effective Attention Sheds Light On Interpretability (2021.findings-acl)
Copied to clipboard
| Challenge: | Using a subset of the GLUE tasks and BERT, we compare the two attention matrices and show that their interpretations differ. |
| Approach: | They propose to use visualizing effective attention to interpret a transformer's behavior since it is more pertinent to the model output by design. |
| Outcome: | The proposed method is more relevant to the model output by design than visualizing attention weights. |
Compositionality of Complex Graphemes in the Undeciphered Proto-Elamite Script using Image and Text Embedding Models (2021.findings-acl)
Copied to clipboard
| Challenge: | a language model over sign images produces more interpretable results than a model over text . a new language model is developed to abstract from human annotators . |
| Approach: | They propose a language modeling architecture which operates over sequences of images or over multimodal sequences with associated labels. |
| Outcome: | The proposed language model can interpret signs in the undeciphered proto-Elamite script . it also provides a novel way to abstract away from biases introduced by human annotators. |
On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers (2021.findings-acl)
Copied to clipboard
Tianchu Ji, Shraddhan Jain, Michael Ferdman, Peter Milder, H. Andrew Schwartz, Niranjan Balasubramanian
| Challenge: | Recent work shows that attention can be pruned to zeros with minimal loss in accuracy. |
| Approach: | They propose a pruning technique which quantizes attention to a 3-bit format without retraining . they find that 80% of attention values can be pruned to zeros with minimal loss in accuracy . |
| Outcome: | The proposed approach produces only a few unique attention values with minimal loss in accuracy. |
Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions? (2021.findings-acl)
Copied to clipboard
| Challenge: | a new task is proposed to modify a model's unethical behavior by communicating context-specific principles of ethics and equity to it. |
| Approach: | They propose a task to amend a questionanswering model's unethical behavior . they use social stereotypes to augment social stereotype models with ethical interventions . |
| Outcome: | The proposed task improves model behavior but fails to generalize to new domains . it is based on a zero-shot evaluation of social stereotypes in reading comprehension systems . |
Unsupervised Label Refinement Improves Dataless Text Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Prior work has shown that dataless classifiers can classify text into categories without using annotated training data. |
| Approach: | They propose a clustering-based approach that assigns a score to any document paired with a label description. |
| Outcome: | The proposed method improves classification performance across multiple datasets and makes it more robust to label descriptions. |
Prompting Contrastive Explanations for Commonsense Reasoning Tasks (2021.findings-acl)
Copied to clipboard
| Challenge: | Large pretrained language models (PLMs) can achieve near-human performance on commonsense reasoning tasks, but provide little human-interpretable evidence of the underlying reasoning they use. |
| Approach: | They propose to use large pretrained language models to generate evidence for commonsense reasoning NLP tasks . they use models to contrast alternative explanations based on key attribute(s) required to justify the correct answer . |
| Outcome: | The proposed model improves performance on two commonsense reasoning benchmarks compared to previous non-contrastive alternatives. |
SMS Spam Detection Through Skip-gram Embeddings and Shallow Networks (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for detecting SMS spam include CNN, Recurrent Neural Networks and CNN. |
| Approach: | They propose a technique for embedding SMS messages into vector spaces suitable for spam detection. |
| Outcome: | The proposed method is competitive with state-of-the-art methods on a UCI Spam Collection dataset. |
Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring (2021.findings-acl)
Copied to clipboard
| Challenge: | despite recent progress, learning new tasks through language instructions remains a challenging problem. |
| Approach: | They propose a hierarchical task learning approach that decomposes task learning into three sub-problems and a model that addresses each sub-probability in a unified manner. |
| Outcome: | The proposed model achieves the state-of-the-art performance on the AL-FRED benchmark . it decomposes task learning into three sub-problems and addresses them in a unified manner . |
Marked Attribute Bias in Natural Language Inference (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing tests for gender-biased word embeddings do not address marked attribute bias . authors propose a new type of intrinsic bias measure for static word embeds . |
| Approach: | They propose a method to detect gender-biased word embeddings in a downstream NLP application . they propose 'debiasing' method to measure the marked attribute bias in embeddable word embeds . |
| Outcome: | The proposed method achieves best results on the marked attribute bias test set. |
VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding (2021.findings-acl)
Copied to clipboard
Hu Xu, Gargi Ghosh, Po-Yao Huang, Prahal Arora, Masoumeh Aminzadeh, Christoph Feichtenhofer, Florian Metze, Luke Zettlemoyer
| Challenge: | Existing methods for multimodal video understanding are task-specific, limiting their use for retrieval-style end tasks. |
| Approach: | They propose a task-agnostic multimodal pre-training approach that can accept video or text input, or both, for a variety of end tasks. |
| Outcome: | The proposed approach outperforms existing methods on a wider range of tasks while maintaining separability. |
Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence (2021.findings-acl)
Copied to clipboard
| Challenge: | a new corpus-level evaluation approach for event extraction is needed in social science applications . human annotations are often required to extract the actions of political actors and actors . a novel corpus evaluation approach can guide creation of similar social science-oriented resources . |
| Approach: | They propose a corpus-based approach to event extraction that integrates corpus evaluation with real-world social science . they use human annotations to read and label every document for mentions of police activity events . |
| Outcome: | The proposed method can guide creation of similar social-science-oriented resources in the future. |
Memory-Efficient Differentiable Transformer Architecture Search (2021.findings-acl)
Copied to clipboard
| Challenge: | Current neural architecture search methods suffer from huge computational cost. |
| Approach: | They propose a reversible recursive backpropagation algorithm that uses the last layer to store the outputs of the network. |
| Outcome: | The proposed algorithm outperforms standard Transformers on three sequence-to-sequence datasets. |
On the Copying Behaviors of Pre-Training for Neural Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies show that initializing NMT models with pre-trained language models (LM) can speed up the model training and boost the model performance. |
| Approach: | They propose a method to control copying behaviors in NMT models by initializing them with pre-trained language models (LM) they propose to use a metric called copy ratio to control the copying behavior in decoding. |
| Outcome: | The proposed method improves translation performance by controlling copying behaviors for pre-training based models. |
Answer Generation for Retrieval-based Question Answering Systems (2021.findings-acl)
Copied to clipboard
| Challenge: | Question Answering systems are a core component of many commercial applications . answer sentence selection (AS2) models are trained to select the best answer sentence . |
| Approach: | They propose to train a sequence to sequence transformer model to generate an answer from a set of candidates. |
| Outcome: | The proposed model improves accuracy by 32 points over the state-of-the-art model on English AS2 datasets. |
Grounding ‘Grounding’ in NLP (2021.findings-acl)
Copied to clipboard
| Challenge: | Cognitive Science defines "grounding" as the process of establishing mutual information between two interlocutors. |
| Approach: | They examine the gaps between NLP and Cognitive Science definitions of "grounding" they propose ways to create new tasks or repurpose existing ones to achieve a more complete sense of grounding . |
| Outcome: | The authors examine the gaps between definitions of grounding and cognitive science . they show that there are ways to improve existing tasks or repurpose existing ones . |
Federated Chinese Word Segmentation with Global Character Associations (2021.findings-acl)
Copied to clipboard
| Challenge: | Chinese word segmentation (CWS) is a fundamental task for natural language processing. |
| Approach: | They propose a neural model for Chinese word segmentation with federated learning to help CWS deal with data isolation. |
| Outcome: | The proposed model outperforms baselines on a simulated environment with five nodes. |
PSED: A Dataset for Selecting Emphasis in Presentation Slides (2021.findings-acl)
Copied to clipboard
Amirreza Shirani, Giai Tran, Hieu Trinh, Franck Dernoncourt, Nedim Lipka, Jose Echevarria, Thamar Solorio, Paul Asente
| Challenge: | null |
| Approach: | null |
| Outcome: | null |
MLMLM: Link Prediction with Mean Likelihood Masked Language Model (2021.findings-acl)
Copied to clipboard
| Challenge: | Knowledge Bases (KBs) are easy to query, verifiable, and interpretable. however, they scale with man-hours and high-quality data. |
| Approach: | They propose to commit the knowledge embedded in MLMs to a KB, making it interpretable . they propose to use a mean likelihood Masked Language Model to compare the likelihood of generating different entities to perform link prediction in a tractable manner. |
| Outcome: | The proposed approach compares the likelihood of generating different entities to perform link prediction in a tractable manner. |
Modulating Language Models with Emotions (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for generating context-aware language that embodies diverse emotions are dull or generic due to limited training data for diverse emotions. |
| Approach: | They propose a modulated layer normalization technique that generates emotional responses using large pre-trained models. |
| Outcome: | The proposed method outperforms baseline methods on the MojiTalk dataset while maintaining diversity, fluency, and coherence. |
Effective Batching for Recurrent Neural Network Grammars (2021.findings-acl)
Copied to clipboard
| Challenge: | RNNGs are hard to scale due to the difficulty of batched training. |
| Approach: | They propose to batch RNNGs where every operation is computed in parallel with tensors across multiple sentences. |
| Outcome: | The proposed RNNG scales faster than existing models and achieves x6 speedup compared to existing C++ DyNet implementation . |
Verb Sense Clustering using Contextualized Word Representations for Semantic Frame Induction (2021.findings-acl)
Copied to clipboard
| Challenge: | Contextualized word representations are effective in many natural language processing tasks, but it remains unclear to what extent they can cover hand-coded semantic information such as semantic frames. |
| Approach: | They compare contextualized word representations with two English frame-semantic resources . they find that several contextualized representations are informative for semantic frame induction . |
| Outcome: | The proposed representations are useful in natural language processing tasks, but are not fully understood by the literature. |
Benchmarking Neural Topic Models: An Empirical Study (2021.findings-acl)
Copied to clipboard
| Challenge: | Neural topic modeling has been attracting much attention recently due to its ability to leverage the advantages of both neural networks and probabilistic topic models. |
| Approach: | They propose to evaluate neural topic models in three tasks using large datasets and a set of metrics to compare them. |
| Outcome: | The proposed models perform better in the first and third tasks than the traditional probabilistic models and are better in many cases. |
Enhancing Chinese Word Segmentation via Pseudo Labels for Practicability (2021.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models alleviate segmentation ambiguity and out-of-vocabulary (OOV) words. |
| Approach: | They propose a semisupervised neural method which distills knowledge from unlabeled data to a student model to improve both in-domain and out-of-domain CWS. |
| Outcome: | The proposed method can keep practicability of the lightweight student model and improve segmentation effectively on downstream Chinese NLP tasks. |
Analysis of Tree-Structured Architectures for Code Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Code generation is the task of generating code snippets from input user specifications written in natural language (NL). |
| Approach: | They evaluate the significance of input parse trees for code generation by using constituency-based parsers as input and an abstract syntax tree as the target. |
| Outcome: | The proposed models on a Python-based code generation dataset and a semantic parsing dataset show that constituency trees encoded using a structure-aware model improve performance. |
How Does Distilled Data Complexity Impact the Quality and Confidence of Non-Autoregressive Machine Translation? (2021.findings-acl)
Copied to clipboard
| Challenge: | Prior work suggests that distilled training data is less complex than manual translations. |
| Approach: | They propose to use sequence-level knowledge distillation to match autoregressive models' translation quality. |
| Outcome: | The proposed model can match translation quality of autoregressive models with distilled training data. |
Leveraging Topic Relatedness for Argument Persuasion (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies of argumentation focus on the effects of factors such as source, audience, and language style, but the impact of exploiting the relationships among controversial topics is under-explored. |
| Approach: | They propose to model topic relatedness among controversial topics using topic embedding features and topic semantics features extracted from the arguments. |
| Outcome: | The proposed method improves predicting persuasiveness and generalizes to rare topics in a few-shot setting. |
One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers (2021.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) have huge model sizes and computational complexity, making it difficult to deploy them to low-latency and high-concurrence online systems. |
| Approach: | They propose a multi-teacher knowledge distillation framework for pre-trained language model compression that can train high-quality student model from multiple teacher PLMs. |
| Outcome: | The proposed framework can train high-quality student model from multiple teacher PLMs with shared pooling and prediction layers to align output space for better collaborative teaching. |
Logic-Consistency Text Generation from Semantic Parses (2021.findings-acl)
Copied to clipboard
| Challenge: | Text generation from semantic parses is challenging due to the complexity of the inner logic and the lack of automatic evaluation metrics for logic consistency. |
| Approach: | They propose a framework for logic consistent text generation from semantic parses that employs iterative training procedures and quality control. |
| Outcome: | The proposed framework enhances logic consistency and human evaluation on two benchmark datasets. |
Inducing Semantic Roles Without Syntax (2021.findings-acl)
Copied to clipboard
| Challenge: | Semantic roles are a key component of linguistic predicate-argument structure, but syntax can be difficult to define, annotate, and predict. |
| Approach: | They propose to use QA-SRL to automatically induce semantic roles from ontologies that use question-answer pairs to represent predicate-argument structure. |
| Outcome: | The proposed method outperforms existing models and a state-of-the-art model over gold syntax. |
Plot and Rework: Modeling Storylines for Visual Storytelling (2021.findings-acl)
Copied to clipboard
| Challenge: | Automated visual storytelling models do not make extensive use of external knowledge and iterative generation when attempting to create stories. |
| Approach: | They propose a framework that uses an image sequence as a story graph to create a coherent story. |
| Outcome: | The proposed framework produces stories superior in diversity, coherence, and humanness . it uses plotting and reworking to improve the model's performance, the authors say . |
Disentangled Code Representation Learning for Multiple Programming Languages (2021.findings-acl)
Copied to clipboard
| Challenge: | Developing effective distributed representations of source code is challenging . current code embedding approaches that represent the semantic and syntax of code are less interpretable . |
| Approach: | They propose a disentangled code representation learning approach to separate the semantic from the syntax of source code under a multi-programming-language setting. |
| Outcome: | The proposed approach achieves better interpretability and generalizability over existing methods. |
Exploring Self-Identified Counseling Expertise in Online Support Forums (2021.findings-acl)
Copied to clipboard
Allison Lahnala, Yuntian Zhao, Charles Welch, Jonathan K. Kummerfeld, Lawrence C An, Kenneth Resnicow, Rada Mihalcea, Verónica Pérez-Rosas
| Challenge: | Increasing number of people engage in online health forums, making it important to understand the quality of the advice they receive. |
| Approach: | They examine the role of expertise in responses to help-seeking posts . they find that a classifier can distinguish between peer and self-identified mental health professionals' interactions . |
| Outcome: | The findings show that experts' language use differs between groups, and that their comments engage the support-seeker further. |
An Investigation of Suitability of Pre-Trained Language Models for Dialogue Generation – Avoiding Discrepancies (2021.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models have been widely used in open-domain dialogue generation. |
| Approach: | They propose to use decoder-only architecture to achieve excellent performance for dialogue generation. |
| Outcome: | The proposed frameworks are based on transformer-ED, transformer-Dec, transformer MLM and transformer-AR. |
Learning to Sample Replacements for ELECTRA Pre-Training (2021.findings-acl)
Copied to clipboard
| Challenge: | Experimental results show that ELECTRA pretrains a discriminator to detect replaced tokens . despite compelling performance, there is no direct feedback loop from discriminator and generator to generator, making replacements biased to correct tokens. |
| Approach: | They propose to augment sampling with a hardness prediction mechanism to encourage the discriminator to learn what it has not acquired. |
| Outcome: | The proposed method improves ELECTRA pre-training on various downstream tasks. |
Reordering Examples Helps during Priming-based Few-Shot Learning (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for learning from limited data are not efficient . we show that presenting examples in the right order is key for generalization . |
| Approach: | They propose a method to learn from limited data using examples as prompts . they propose PERO, which uses examples as search over set of permutations . |
| Outcome: | The proposed method can generalize using as few as 10 examples, the authors show . it can be used on sentiment classification, natural language inference and fact retrieval tasks . |
Constrained Labeled Data Generation for Low-Resource Named Entity Recognition (2021.findings-acl)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) in lowresource languages has been a challenge for years . Existing methods suffer from low quality of annotated data in target language . |
| Approach: | They propose a method that uses projected annotations to generate pseudo supervised data with a transformer language model and a constrained beam search. |
| Outcome: | The proposed method achieves state-of-the-art or competitive performance in low-resource languages. |
He is very intelligent, she is very beautiful? On Mitigating Social Biases in Language Modelling and Generation (2021.findings-acl)
Copied to clipboard
Aparna Garimella, Akhash Amarnath, Kiran Kumar, Akash Pramod Yalla, Anandhavelu N, Niyati Chhaya, Balaji Vasan Srinivasan
| Challenge: | Existing studies have focused on mitigating social biases in context-free representations, with recent shift to contextual ones. |
| Approach: | They propose an approach to mitigate social biases in a large pre-trained contextual language model . they propose lexical co-occurrence-based bias penalization in the decoder units . |
| Outcome: | The proposed approach reduces biases in fill-in-the-blank sentences and summarizes . it also reduces the biased representations in the frameworks, the authors show . |
Task-adaptive Pre-training of Language Models with Word Embedding Regularization (2021.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models acquire domain-independent knowledge through pre-training with massive textual resources. |
| Approach: | They propose a task-adaptive pre-training process that makes static embeddings close to the word embedds obtained in the target domain. |
| Outcome: | The proposed process improves on BioASQ and SQuAD when the pre-training corpora were not dominated by indomain data. |
Do Grammatical Error Correction Models Realize Grammatical Generalization? (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models for grammatical error correction use pseudo data, but they are inconvenient for realworld deployment due to large amounts of training data. |
| Approach: | They propose a method to evaluate whether GEC models can generalize to unseen errors by using synthetic and real GEC datasets with controlled vocabularies. |
| Outcome: | The proposed model fails to realize grammatical generalization even in simple settings with limited vocabulary and syntax, suggesting it lacks the generalization ability required to correct errors from provided training examples. |
Domain-Aware Dependency Parsing for Questions (2021.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained parsers perform poorly on domain-specific questions, a paper argues . retraining parser with domain- specific questions is expensive, as these require linguistic expertise. |
| Approach: | They propose an automatic labeled domain question generation framework leveraging domain knowledge and seed domain questions. |
| Outcome: | The proposed framework improves state-of-the-art parsers on domain questions. |
Using Social and Linguistic Information to Adapt Pretrained Representations for Political Perspective Identification (2021.findings-acl)
Copied to clipboard
| Challenge: | a new framework for political perspective detection is proposed to improve text training costs . current deep learning models lack the ability to focus on text span for bias detection . |
| Approach: | They propose a framework that pretrains the text model using social and linguistic contexts . they demonstrate that the framework improves performance by identifying bias-related text spans based on entity mentions and news sharing . |
| Outcome: | The proposed framework improves on two news bias datasets and improves performance on the general source and task. |
Enhancing Dialogue-based Relation Extraction by Speaker and Trigger Words Prediction (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for identifying relations from dialogues do not fully consider the particularity of dialogues, making them difficult to understand the semantics between conversational arguments. |
| Approach: | They propose two tasks to enhance the extraction of dialogue-based relations . speaker prediction captures the characteristics of speakerrelated entities . the trigger words prediction provides supportive contexts for relations between arguments . |
| Outcome: | The proposed tasks improve the extraction of dialogue-based relations . speaker prediction captures the characteristics of speakerrelated entities . the trigger words prediction provides supportive contexts for relations between arguments . |
Modeling Event-Pair Relations in External Knowledge Graphs for Script Reasoning (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods focus on graph triples with event overlap, but ignore more supportive triples . Script reasoning relies on understanding the relationship between two events . |
| Approach: | They propose a model to learn the inferential relations between events from the whole eventuality KG . they propose 'script adapter' to extend the model to infer the associated relations between an event chain and a subsequent event candidate. |
| Outcome: | The proposed model is compared with baselines using external KG or not on a script reasoning task. |
PROST: Physical Reasoning about Objects through Space and Time (2021.findings-acl)
Copied to clipboard
| Challenge: | a new dataset is available to test pretraining of physical reasoning models . state-of-the-art models are inadequate at reasoning about physical interactions, authors say . |
| Approach: | They present a dataset that contains 18,736 multiple-choice questions from 14 templates . they propose to use the dataset to probe both causal and masked language models . |
| Outcome: | The proposed dataset contains 18,736 multiple-choice questions covering 10 physical reasoning concepts. |
Revisiting the Evaluation of End-to-end Event Extraction (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing EE research uses the role-averaged evaluation metric, but it is misleading to downstream applications. |
| Approach: | They propose two new evaluation metrics that explicitly penalize wrongly identified event arguments. |
| Outcome: | The proposed evaluation metrics improve the initial evaluation by 10% . the proposed training scheme is better than the existing one, the authors show . |
Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to simultaneous speech-to-text translation suffer from error propagation and extra latency. |
| Approach: | They propose a new paradigm for simultaneous speech-to-text translation using two separate decoders . they use multitask learning to jointly learn these two tasks with a shared encoder . |
| Outcome: | The proposed method achieves substantially better translation quality at similar levels of latency. |
HIT - A Hierarchically Fused Deep Attention Network for Robust Code-mixed Language Representation (2021.findings-acl)
Copied to clipboard
| Challenge: | linguistics and morphology of resource-short code-mixed texts remain a key challenge in text processing. |
| Approach: | They propose a hierarchical transformer-based framework that captures the semantic relationship among words and hierarchically learns sentencelevel semantics using a fused attention mechanism. |
| Outcome: | The proposed framework improves on one European and five Indic languages on four NLP tasks on eleven datasets. |
Semi-Supervised Data Programming with Subset Selection (2021.findings-acl)
Copied to clipboard
| Challenge: | Several approaches to improve annotation cost have been proposed to use large amounts of labelled training data. |
| Approach: | They propose a semi-supervised data programming paradigm that uses weak supervision and semi-supervised loss functions to augment small amounts of labelled data with a large unlabelled dataset. |
| Outcome: | The proposed framework outperforms the current state-of-the-art on seven publicly available datasets. |
Fingerprinting Fine-tuned Language Models in the Wild (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing fingerprinting methods to fingerprint language models are limited to attributing organic text . however, fine-tuned LMs can generate long, coherent, and grammatically valid synthetic text. |
| Approach: | They conduct extensive experiments to demonstrate the limitations of existing fingerprinting approaches. |
| Outcome: | The proposed fingerprinting methods are limited to attributing synthetic text generated by 10 pre-trained LMs. |
Analyzing Code Embeddings for Coding Clinical Narratives (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent work on automated ICD coding learn mappings between low-dimensional representations of clinical text reports and codes. |
| Approach: | They propose novel neural networks for encoding medical codes based on textual, structural and statistical characteristics using a single deep learning baseline model. |
| Outcome: | The proposed methods improve the accuracy of medical codes based on their textual, structural and statistical characteristics. |
Automatic Construction of Sememe Knowledge Bases via Dictionaries (2021.findings-acl)
Copied to clipboard
| Challenge: | Sememe knowledge bases (SKBs) are used to analyze natural language processing. |
| Approach: | They propose a method to build sememe knowledge bases from an existing dictionary . they propose to use existing dictionaries to build an English and a French SKB . |
| Outcome: | The proposed method is superior to HowNet, the most widely used SKB that takes decades to build manually. |
Rule-Aware Reinforcement Learning for Knowledge Graph Reasoning (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to reason missing facts on Knowledge Graphs face with serious incompleteness due to their black-box nature. |
| Approach: | They propose a multi-hop reasoning method that injects high quality symbolic rules into the model's reasoning process and employs partially random beam search. |
| Outcome: | The proposed method outperforms existing multi-hop reasoning methods in terms of Hit@1 and MRR. |
XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages (2021.findings-acl)
Copied to clipboard
Tahmid Hasan, Abhik Bhattacharjee, Md. Saiful Islam, Kazi Mubasshir, Yuan-Fang Li, Yong-Bin Kang, M. Sohel Rahman, Rifat Shahriyar
| Challenge: | XL-Sum dataset covers 44 languages ranging from low to high-resource . Xl-SUM is highly abstractive, concise, and of high quality . |
| Approach: | They present a dataset comprising 1 million professionally annotated article-summary pairs from BBC . they fine-tune a pretrained multilingual model with XL-Sum and experiment on multilingual and lowresource tasks. |
| Outcome: | The proposed dataset is highly abstractive, concise, and of high quality . it shows higher scores on 10 languages than similar datasets compared to monolingual ones . |
Use of Formal Ethical Reviews in NLP Literature: Historical Trends and Current Practices (2021.findings-acl)
Copied to clipboard
| Challenge: | Ethical aspects of research in language technologies have received much attention recently . do we observe a rise in formal ethical reviews of NLP studies? |
| Approach: | They conduct a qualitative and quantitative analysis of the ethics of NLP research . they compare the ethical reviews of NLAs to those of related disciplines . |
| Outcome: | The results compare the ACL Anthology to other related disciplines in the field . the results show that there is a heightened awareness of ethical issues that was previously lacking . |
As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Mistranslated numbers can cause financial loss or medical misinformation. |
| Approach: | They propose a method to assess the robustness of neural machine translation systems to numerical text via behavioural testing. |
| Outcome: | The proposed method systematically assesses four fundamental capabilities of neural machine translation systems in translation numbers by virtue of a variety of test cases. |
Investigating Memorization of Conspiracy Theories in Text Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies examine conspiracy theories in social media, but they have not evaluated their presence in generative language models. |
| Approach: | They examine the ability of generative language models to generate conspiracy theory text . they highlight the difficulties of this task and discuss the drawbacks . |
| Outcome: | The proposed model can generate conspiracy theories without access to training data. |
A Text-Centered Shared-Private Framework via Cross-Modal Prediction for Multimodal Sentiment Analysis (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies treat all three modal features equally and implicitly explore the interactions between different modalities. |
| Approach: | They propose a text-centered shared-private framework for multimodal fusion . they propose modalities that can provide shared and private semantics . |
| Outcome: | The proposed framework outperforms baselines on the MOSEI and MOSI datasets. |
What Would a Teacher Do? Predicting Future Talk Moves (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in natural language processing (NLP) have the ability to transform how classroom learning takes place. |
| Approach: | They propose a task that uses the academically productive talk framework to learn strategies that make for the best learning experience. |
| Outcome: | The proposed task outperforms baselines on academically productive talk (FTMP) and shows that it outperformed human performance on FTMP. |
BioGen: Generating Biography Summary under Table Guidance on Wikipedia (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for summarizing text have not captured the salient information from an article. |
| Approach: | They propose a table-guided abstractive biography summarization that utilizes factual tables to capture important information and generate a summary of a biography. |
| Outcome: | The proposed method is the first large-scale biography summarization dataset with tables. |
Multilingual Simultaneous Neural Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Simultaneous machine translation (SIMT) involves translating source utterances to the target language in real-time before the speaker utterrance completes. |
| Approach: | They propose a multilingual approach to simultaneous machine translation where a single model simultaneously translates between multiple languages. |
| Outcome: | The proposed multilingual approach improves on two Germanic and three Romance languages and is on-par or better than the universal model trained for all languages. |
Cross-Domain Review Generation for Aspect-Based Sentiment Analysis (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing domain adaptation methods for Aspect-Based Sentiment Analysis lack finegrained labeled data. |
| Approach: | They propose a new domain adaptation paradigm called cross-domain review generation which aims to generate target-domain reviews with fine-grained annotation based on the labeled source domain. |
| Outcome: | The proposed approach is superior to state-of-the-art domain adaptation methods. |
On the Language Coverage Bias for Neural Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Language coverage bias is important for neural machine translation because of the target-original training data. |
| Approach: | They propose two approaches to alleviate the language coverage bias problem by explicitly distinguishing between the source-and target-original training data. |
| Outcome: | The proposed methods improve translation tasks on both back-and forward-translation and their tagged variants. |
Named Entity Recognition via Noise Aware Training Mechanism with Data Filter (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for named entity recognition (NER) do not distinguish noisy from hard samples. |
| Approach: | They propose a noise-aware-with-filter method to help model identify noisy samples . they propose 'incomplete trust' loss function which boosts L CRF with a robust term . |
| Outcome: | The proposed method outperforms the existing methods on six real-world Chinese and English NER datasets. |
A Multi-Task Approach for Improving Biomedical Named Entity Recognition by Incorporating Multi-Granularity information (2021.findings-acl)
Copied to clipboard
| Challenge: | Neural named entity recognition (BioNER) methods require large amount of annotated data, while the annotating BioNER datasets are often difficult to obtain and small in scale due to the limitations of privacy, ethics and high degree of specialization. |
| Approach: | They propose a method that utilizes latent multi-granularity information in annotated bioNER datasets to alleviate the lack of training samples. |
| Outcome: | The proposed model improves over the BioBERT baseline and can get more than 3% improvement of F1score in low-resource scenarios. |
EBERT: Efficient BERT Inference with Dynamic Structured Pruning (2021.findings-acl)
Copied to clipboard
| Challenge: | Pruning has been demonstrated as an effective way of reducing computational complexity for deep networks, especially CNNs for computer vision tasks. |
| Approach: | They propose a dynamic structured pruning algorithm that prunes model weights at run-time . they propose to prune the unimportant heads in multi-head self-attention layers . |
| Outcome: | The proposed algorithm outperforms state-of-the-art methods on different tasks. |
Strong and Light Baseline Models for Fact-Checking Joint Inference (2021.findings-acl)
Copied to clipboard
| Challenge: | Automated fact checking is rapidly gaining attention of the NLP and AI communities. |
| Approach: | They propose lightweight strong baselines for automated fact-checking systems . they propose to combine multiple pieces of evidence to verify a claim . |
| Outcome: | The proposed methods outperform heavier models on the leaderboard with blind TEST set. |
Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for table-to-text generation suffer from poor faithfulness and low coverage. |
| Approach: | They propose a method that combines Autoregressive and Non-Autoregressive generation to generate a table-to-text from a key-value table using a skeleton and an edit-based non-autoregressively generation model. |
| Outcome: | The proposed method outperforms the existing methods on WikiPerson and WikiBio datasets on coverage and faithfulness. |
TILGAN: Transformer-based Implicit Latent GAN for Diverse and Coherent Text Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing autoregressive models suffer from the exposure bias problem due to mismatches between training and generation stages. |
| Approach: | They propose a Transformerbased Implicit Latent GAN which combines a transformer autoencoder and GAN in the latent space with a novel design and distribution matching based on the Kullback-Leibler divergence. |
| Outcome: | The proposed model improves local and global coherence and quality-diversity trade-off on three benchmark datasets. |
John praised Mary because _he_? Implicit Causality Bias and Its Interaction with Explicit Cues in LMs (2021.findings-acl)
Copied to clipboard
| Challenge: | Psycholinguists have identified one such cue in the implicit causality bias of interpersonal verbs. |
| Approach: | They propose to use pre-trained language models to encode IC bias at inference time . they hypothesize that when a cause is explicitly stated, an incongruent IC biased leads to a delay in human processing. |
| Outcome: | The results suggest that pre-trained language models tend to prioritize lexical patterns over higher-order signals. |
Do It Once: An Embarrassingly Simple Joint Matching Approach to Response Selection (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing matching models for response selection perform the independent matching (IM) approach. Existing models for matching only perform one match regardless of the number of options. |
| Approach: | They propose a joint matching approach which performs matching only once regardless of the number of options. |
| Outcome: | The proposed approach outperforms existing models and reduces training time by over half. |
Climbing the Tower of Treebanks: Improving Low-Resource Dependency Parsing via Hierarchical Source Selection (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent work on multilingual dependency parsing focused on developing highly multilingual parsers . a recent major paradigm shift in NLP towards largescale pretrained language models has reduced the downstream relevance of supervised syntactic parse. |
| Approach: | They propose a heuristic approach to multilingual dependency parsing that heurs out the "one model to rule them all" approach by hierarchically clustering all Universal Dependencies languages based on their syntactic similarity . |
| Outcome: | The proposed approach outperforms a "one model to rule them all" approach with a heuristic selection of languages and treebanks for a target language. |
Enhancing the Open-Domain Dialogue Evaluation in Latent Space (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to evaluate opendomain dialogues are limited due to the one-to-many nature of dialogues. |
| Approach: | They propose a self-supervised setting to obtain a smooth latent space that captures discourse-level context information and implicitly models more references in latent spaces. |
| Outcome: | The proposed method outperforms baseline methods on two real-world dialogue datasets. |
Adapting Monolingual Models: Data can be Scarce when Language Similarity is High (2021.findings-acl)
Copied to clipboard
| Challenge: | Large pre-trained language models are the dominant approach for solving many tasks in natural language processing. |
| Approach: | They propose to retrain the lexical layers of four BERT-based models using data from two low-resource target languages while the Transformer layers are independently finetuned on a POS-tagging task in the model's source language. |
| Outcome: | The proposed method achieves high performance for both target and target languages with high similarity. |
BatchMixup: Improving Training by Interpolating Hidden States of the Entire Mini-batch (2021.findings-acl)
Copied to clipboard
| Challenge: | a data augmentation technique is used to augment data, but it has two drawbacks. |
| Approach: | They propose a new mixup paradigm that generates new points scattered throughout the whole mini-batch. |
| Outcome: | The proposed model improves the performance of NLP tasks while using different ratios of training data. |
DocNLI: A Large-scale Dataset for Document-level Natural Language Inference (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on sentence-level inference, which limits its application in downstream NLP problems. |
| Approach: | They propose to construct a large-scale dataset for document-level NLI that can be used to study NLP problems. |
| Outcome: | The proposed model performs well on popular sentence-level benchmarks and generalizes well to out-of-domain NLP tasks that rely on inference at document granularity. |
Rule Augmented Unsupervised Constituency Parsing (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have shown that unsupervised parsing methods do not learn meaningful semantics (not even simple grammar) |
| Approach: | They propose an approach that utilizes very generic linguistic knowledge of the language present in the form of syntactic grammar rules and is independent of the base system. |
| Outcome: | The proposed model is independent of the base system and takes advantage of syntactic grammar rules. |
Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalan (2021.findings-acl)
Copied to clipboard
Jordi Armengol-Estapé, Casimiro Pio Carrino, Carlos Rodriguez-Penagos, Ona de Gibert Bonet, Carme Armentano-Oller, Aitor Gonzalez-Agirre, Maite Melero, Marta Villegas
| Challenge: | Multilingual language models have been a crucial breakthrough for under-resourced languages . however, the superiority of language-specific models has already been proven for underresourced ones . |
| Approach: | They propose to build a monolingual monolingual model that is comparable to state-of-the-art large multilingual models. |
| Outcome: | The proposed model consistently outperforms state-of-the-art models across tasks and settings. |
How transfer learning impacts linguistic knowledge in deep NLP models? (2021.findings-acl)
Copied to clipboard
| Challenge: | Several researchers have shown that deep NLP models learn non-trivial amount of linguistic knowledge, captured at different layers of the model. |
| Approach: | They propose to fine-tune pre-trained models towards downstream NLP tasks to capture linguistic knowledge. |
| Outcome: | The proposed model is adapted to GLUE tasks and retains linguistic information in the network while forgetting it. |
Language Models Use Monotonicity to Assess NPI Licensing (2021.findings-acl)
Copied to clipboard
| Challenge: | Neural language models (LMs) have become powerful approximators of human language . fewer studies have been done on what kind of formal semantic features are encoded by LMs . |
| Approach: | They propose a series of experiments that investigate the semantic knowledge of language models . they use diagnostic classifiers, linguistic acceptability tasks and a ranking method to investigate the models' inner workings. |
| Outcome: | The proposed method can be applied to LMs trained on filtered corpora and gain stronger insights into their generalizations. |
Slot Transferability for Cross-domain Slot Filling (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing work on slot filling uses labeled data from source domains to train a model for target domains. |
| Approach: | They propose a model-agnostic Slot Transferability Measure (STM) to evaluate the transferability from a source slot to a target slot. |
| Outcome: | The proposed method outperforms state-of-the-art models on multiple datasets and models. |
Word Graph Guided Summarization for Radiology Findings (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on introducing salient word information to general text summarization framework to guide selection of key content in radiology findings. |
| Approach: | They propose a method for automatic impression generation using word graphs and a Word Graph guided Summarization model to capture critical words and their relations. |
| Outcome: | The proposed method is validated on two datasets, OPENI and MIMIC-CXR. |
Generalized Supervised Attention for Text Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing supervised attention methods that use human knowledge to learn better alignments are costly or infeasible. |
| Approach: | They propose a generalized supervised attention method based on quasi alignments that are easier to obtain than ideal alignments. |
| Outcome: | The proposed framework improves generation performance and is robust against errors in attention supervision. |
Uncertainty Aware Review Hallucination for Science Article Classification (2021.findings-acl)
Copied to clipboard
Korbinian Friedl, Georgios Rizos, Lukas Stappen, Madina Hasan, Lucia Specia, Thomas Hain, Björn Schuller
| Challenge: | Existing approaches to peer review support are limited in their use of available information and subjectivity. |
| Approach: | They propose to use aleatory uncertainty and loss importance interpolations to model review representations at test time to provide a realistic evaluation framework. |
| Outcome: | The proposed framework makes better use of the available information and is realistic with respect to the limitations set by the task 1 . |
Automatically Select Emotion for Response via Personality-affected Emotion Transition (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on rendering specified emotions in responses, yet the individual difference in emotion expression is overlooked. |
| Approach: | They propose to equip a dialog system with personality and enable it to select emotions in responses like humans. |
| Outcome: | The proposed system can select emotions in responses like humans by simulating the emotion transition of humans in conversation. |
Highlight-Transformer: Leveraging Key Phrase Aware Attention to Improve Abstractive Multi-Document Summarization (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models do not consider key phrases in determining attention weights of self-attention . Existing work does not consider the importance of key phrases when determining weights . |
| Approach: | They propose a model with highlighting mechanism to assign greater attention weights to key phrases . they propose two structures of highlighting attention for each head and the multihead highlighting . experimental results show that their proposed model significantly outperforms the baseline model . |
| Outcome: | The proposed model outperforms the baseline models on a multi-news dataset. |
Phrase-Level Action Reinforcement Learning for Neural Dialog Response Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for dialog agent training lack a robust action space for entangled information, which can cause bias and deviate from natural human language. |
| Approach: | They propose phrase-level action reinforcement learning which allows the model to alter the sentence structure and content with the sequential action selection. |
| Outcome: | The proposed model achieves competitive results with state-of-the-art models on the MultiWOZ dataset, indicating that it is effective for solving task-oriented dialogs. |
Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights (2021.findings-acl)
Copied to clipboard
| Challenge: | In this paper, we propose the first large scale study of automatic speech recognition in Sanskrit . we focus on the impact of unit selection in San's ASR systems . |
| Approach: | They propose a large scale study of automatic speech recognition in Sanskrit . they propose syllable level unit selection that captures character sequences . |
| Outcome: | The proposed model captures character sequences from one vowel in the word to the next vowela. |
Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for learning task-oriented dialog systems filter irrelevant KB information over a large KB. |
| Approach: | They propose a pairwise similarity filter that respects the n-ary structure in a KB record and an auxiliary loss that helps in separating contextually unrelated KB information. |
| Outcome: | The proposed method outperforms existing state-of-the-art models on three publicly available datasets. |
DialogSum: A Real-Life Scenario Dialogue Summarization Dataset (2021.findings-acl)
Copied to clipboard
| Challenge: | Experimental results show unique challenges in dialogue summarization such as spoken terms, special discourse structures, coreferences and ellipsis, pragmatics and social common sense. |
| Approach: | They propose a large-scale labeled dialogue summarization dataset . they use state-of-the-art neural models to analyze spoken dialogue summaries . |
| Outcome: | The proposed dataset can be used to analyze spoken dialogue summarization challenges. |
What Did You Refer to? Evaluating Co-References in Dialogue (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing neural end-to-end dialogue models have limitations on exactly interpreting the linguistic structures in dialogue history context. |
| Approach: | They propose to directly measure the capability of neural end-to-end dialogue models on understanding the entity-oriented structures via question answering. |
| Outcome: | The proposed model can understand large-scale English and Chinese human human dialogues using a large-format dataset. |
Beyond Metadata: What Paper Authors Say About Corpora They Use (2021.findings-acl)
Copied to clipboard
| Challenge: | Currently, dataset retrieval relies almost exclusively on metadata provided by the publishers. |
| Approach: | They propose to use metadata to extract review statements from scientific publications . they argue that a crucial piece of information is missing to inform the examination of search results . |
| Outcome: | The proposed analysis is the first of its kind in the field of Natural Language Processing. |
Knowledge Distillation for Quality Estimation (2021.findings-acl)
Copied to clipboard
Amit Gajbhiye, Marina Fomicheva, Fernando Alva-Manchego, Frédéric Blain, Abiola Obamuyide, Nikolaos Aletras, Lucia Specia
| Challenge: | Recent success in Quality Estimation stems from the use of multilingual pre-trained models, where large models lead to impressive results. |
| Approach: | They propose to transfer knowledge from a strong QE teacher model to a much smaller model with a different, shallower architecture. |
| Outcome: | The proposed model performs better than distilled models with 8x fewer parameters. |
Cross-document Coreference Resolution over Predicted Mentions (2021.findings-acl)
Copied to clipboard
| Challenge: | Cross-document coreference resolution has been under-explored in recent years . however, the challenge of cross-document resolution remains relatively under-studied . |
| Approach: | They propose a model for cross-document coreference resolution from raw text that extends a prominent withindocument corefer model to the CD setting. |
| Outcome: | The proposed model achieves competitive results for event and entity coreference resolution on gold mentions. |
Controllable Abstractive Dialogue Summarization with Sketch Supervision (2021.findings-acl)
Copied to clipboard
| Challenge: | Using a model to generate summary sketches, we improve abstractive dialogue summarization quality and enable granularity control. |
| Approach: | They propose a model that generates a preliminary summary sketch and a strategy to control granularity. |
| Outcome: | The proposed model achieves state-of-the-art on the largest dialogue summarization corpus with as high as 50.79 in ROUGE-L score. |
Elaborative Simplification: Content Addition and Explanation Generation in Text Simplification (2021.findings-acl)
Copied to clipboard
| Challenge: | a new study examines the use of content addition in text simplification when complex concepts need to be explained. |
| Approach: | They present a data-driven study of content addition in text simplification . they analyze 1.3K instances of elaborative simplification in the Newsela corpus . |
| Outcome: | The proposed study shows that contextual specificity can improve elaboration generation performance. |
Could you give me a hint ? Generating inference graphs for defeasible reasoning (2021.findings-acl)
Copied to clipboard
| Challenge: | Defeasible reasoning is a mode of reasoning where conclusions can be overturned by taking into account new evidence. |
| Approach: | They propose to automatically generate inference graphs for a defeasible inference task by transfer learning from a related NLP task. |
| Outcome: | The proposed method generates meaningful graphs for a defeasible inference task and human accuracy improves by 20%. |
Characterizing Social Spambots by their Human Traits (2021.findings-acl)
Copied to clipboard
| Challenge: | Social spambots are an emerging class of spammers attempting to emulate people . previous studies show that standard spambot detection methods fail to distinguish them from genuine accounts . |
| Approach: | They hypothesize that human-like attributes of social spambots are unhuman-like . they find that social spam bots are extremely similar and average in their expressed personality, demographics, and emotion . |
| Outcome: | The proposed method is based on the human characteristics of social spambots . it shows that social bots are extremely similar and average in their expressed personality, demographics, and emotion . |