Papers with deep learning models
Investigating the Multilingual Calibration Effects of Language Model Instruction Tuning (2026.eacl-short)
Copied to clipboard
Jerry Huang, Peng Lu, Qiuhao Zeng, Yusuke Iwasawa, Yutaka Matsuo, Sarath Chandar, Edison Marrese-Taylor, Irene Li
| Challenge: | despite advances in foundation model research, the relationship between large language models and their calibration remains an open area of research. |
| Approach: | They examine a gap in the calibration of large language models within multilingual settings to better understand how data scarcity can potentially lead to different calibration effects. |
| Outcome: | The proposed calibration gap is found in two multilingual benchmarks over 29 and 42 languages. |
NLP+Vis: NLP Meets Visualization (2023.emnlp-tutorial)
Copied to clipboard
| Challenge: | This tutorial will introduce NLP+Vis with a focus on two main threads of work: NLP for Vis and Vis for NLP. |
| Approach: | tutorial will introduce NLP+Vis with a focus on two main threads of work . overview of research topics on combining NLP and Vis techniques will be covered . |
| Outcome: | The tutorial will introduce NLP+Vis with a focus on two main threads of work . it will provide an overview of research topics on combining NLP and Vis techniques . |
LogicSolver: Towards Interpretable Math Word Problem Solving with Logical Prompt-enhanced Learning (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in MWP solving are uninterpretable due to shallow heuristics . a new approach to solve automatic word problem solvers requires a solver to predict expression tree and corresponding linguistic logic formulas simultaneously. |
| Approach: | They propose to annotate interpretable logical formulas based on algebraic knowledge as the grounded linguistic logic of each solution equation. |
| Outcome: | The proposed approach improves interpretability of a MWP solver by using logical prompts and interpretation generation. |
Deep Learning for Natural Language Inference (N19-5)
Copied to clipboard
| Challenge: | This tutorial discusses cutting-edge research on NLI, including recent advance on dataset development, cutting- edge deep learning models, and highlights from recent research on using NLI to understand capabilities and limits of deep learning for language understanding and reasoning. |
| Approach: | This tutorial discusses cutting-edge research on NLI, including recent advance on dataset development and cutting- edge deep learning models. |
| Outcome: | This tutorial discusses cutting-edge research on NLI, including recent advance on dataset development, cutting- edge deep learning models, and highlights from recent research on using NLI to understand capabilities and limits of deep learning model for language understanding and reasoning. |
Automatic Construction of Enterprise Knowledge Base (2021.emnlp-demo)
Copied to clipboard
| Challenge: | Existing knowledge bases are often based on bootstrapping entities from human-curated sources such as Wikipedia. |
| Approach: | They propose to build a knowledge base from enterprise documents with minimal human intervention by using deep learning models and classical machine learning techniques. |
| Outcome: | The proposed system is currently serving as part of a Microsoft 365 service. |
Deep Learning Approaches to Text Production (N18-6)
Copied to clipboard
| Challenge: | Text production is a key component of many NLP applications . Claire Gardent is based in France and is pursuing research in text production . |
| Approach: | This tutorial will cover the fundamentals and state-of-the-art research on neural models for text production. |
| Outcome: | This tutorial will cover the fundamentals and the state-of-the-art research on neural models for text production. |
Meta Learning and Its Applications to Natural Language Processing (2021.acl-tutorials)
Copied to clipboard
| Challenge: | Meta-learning is a new technique that aims to learn better learning algorithms, including better parameter initialization, optimization strategy, network architecture, distance metrics, and beyond. |
| Approach: | This tutorial introduces Meta-learning approaches and the theory behind them, and then reviews the works of applying this technology to NLP problems. |
| Outcome: | This tutorial will introduce Meta-learning approaches and the theory behind them, and then review the works of applying this technology to NLP problems. |
A logical-based corpus for cross-lingual evaluation (D19-61)
Copied to clipboard
| Challenge: | a recent study shows that deep learning models can be used to solve textual inference tasks using simple linguistic patterns. |
| Approach: | They propose a set of syntactic tasks focused on contradiction detection that exploit linguistic patterns. |
| Outcome: | The proposed tasks can be implemented in English and Portuguese. |
On the Effectiveness of the Pooling Methods for Biomedical Relation Extraction with Deep Learning (D19-62)
Copied to clipboard
| Challenge: | Existing models for relation extraction use different pooling mechanisms to perform pooling for RE. |
| Approach: | They conduct a comprehensive study to evaluate the effectiveness of different pooling mechanisms for deep learning in biomedical RE. |
| Outcome: | The proposed model outperforms the previous models on two biomedical datasets. |
AutoRC: Improving BERT Based Relation Classification Models via Architecture Search (2021.acl-srw)
Copied to clipboard
| Challenge: | Existing literature on relation classification models shows no consensus on optimal architecture . |
| Approach: | They propose a search space for BERT based relation classification models and employ an ENAS method to find better architectures. |
| Outcome: | The proposed method can find better architectures than baseline models on eight benchmark RC tasks. |
Forecasting Firm Material Events from 8-K Reports (D19-51)
Copied to clipboard
| Challenge: | In this paper, we show deep learning models can be used to forecast firm material event sequences based on the contents of the company’s 8-K Current Reports. |
| Approach: | They exploit state-of-the-art neural architectures, including sequence-to-sequence architecture and attention mechanisms, to build a deep learning model that can forecast firm material event sequences based on company 8-K Current Reports. |
| Outcome: | The proposed model can forecast firm material event sequences based on the contents of the firm's 8-K Current Reports. |
InstructCoder: Instruction Tuning Large Language Models for Code Editing (2024.acl-srw)
Copied to clipboard
| Challenge: | InstructCoder is the first instruction-tuning dataset designed to adapt LLMs for general-purpose code editing. |
| Approach: | They propose to use Large Language Models to edit code based on user instructions . they use a dataset to adapt LLMs to general-purpose code editing . |
| Outcome: | The proposed model can significantly improve code editing performance compared to proprietary models . the proposed model is based on a human-written execution-based benchmark . |
An Embarrassingly Simple Approach for Intellectual Property Rights Protection on Recurrent Neural Networks (2022.aacl-main)
Copied to clipboard
| Challenge: | Existing protection schemes for deep neural network models protect intellectual property rights from being abused, stolen and plagiarized. |
| Approach: | They propose a practical approach for the IPR protection on recurrent neural networks without all the bells and whistles of existing IPR solutions. |
| Outcome: | The proposed approach is robust and effective against ambiguity and removal attacks on different RNN variants. |
A Study on Entity Resolution for Email Conversations (2020.lrec-1)
Copied to clipboard
| Challenge: | This paper addresses the task of entity resolution in email conversations. |
| Approach: | They propose to create an annotated seed corpus of email threads labeled with entity coreference chains and evaluate their models for the task. |
| Outcome: | The proposed model performs well on the entity resolution task for email conversations. |
On the Interpretability of Deep Learning Models for Collaborative Argumentation Analysis in Classrooms (2024.acl-srw)
Copied to clipboard
| Challenge: | Existing models for collaborative argumentation lack interpretability and teachers are skeptics about their use. |
| Approach: | They propose to use four explainable AI methods to provide models for automated analysis of argument moves and specificity levels within collaborative argumentation to cultivate trust among teachers. |
| Outcome: | The proposed models perform exceptionally well in analyzing word contributions and demonstrating that the models can be explained by a user-interface. |
SPARQL-to-Text Question Generation for Knowledge-Based Conversational Applications (2022.aacl-main)
Copied to clipboard
| Challenge: | a paper focuses on the generation of natural language questions based on SPARQL queries . knowledge-based approaches have become popular in the field of question answering and dialogue . |
| Approach: | This paper focuses on the generation of natural language questions based on SPARQL queries . it uses 4 knowledge-based QA corpora homogenized for the task and a new challenge set is introduced . |
| Outcome: | The proposed task is based on the generation of questions in a conversational context. |
Does BERT Know that the IS-A Relation Is Transitive? (2022.acl-short)
Copied to clipboard
| Challenge: | Recent studies suggest pre-trained BERT can capture lexico-semantic clues from words in context. |
| Approach: | They examine word senses and the transitive property of IS-A relation . they aim to quantify how much BERT agrees with transitivity property . |
| Outcome: | The proposed model can capture lexico-semantic clues from words in context . but to what extent it captures transitive nature of some lexical relations is unclear . |
BullStop: A Mobile App for Cyberbullying Prevention (2020.coling-demos)
Copied to clipboard
| Challenge: | Existing tools to combat cyberbullying mostly use wordlists or lack flexibility to cope with the evolving nature of social media. |
| Approach: | BullStop is a mobile app for detecting and preventing cyberbullying and online abuse on social media platforms. |
| Outcome: | BullStop detects and prevents cyberbullying and online abuse on social media platforms and can automatically initiate actions such as deleting offensive messages and blocking bullies on behalf of the user. |
The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding (2020.acl-demos)
Copied to clipboard
Xiaodong Liu, Yu Wang, Jianshu Ji, Hao Cheng, Xueyun Zhu, Emmanuel Awa, Pengcheng He, Weizhu Chen, Hoifung Poon, Guihong Cao, Jianfeng Gao
| Challenge: | MT-DNN is an open-source natural language understanding toolkit . it allows researchers and developers to train customized deep learning models . |
| Approach: | They present MT-DNN, an open-source natural language understanding toolkit . it is designed to facilitate rapid customization for a broad spectrum of NLU tasks . MT supports multi-task knowledge distillation, which can substantially compress a deep neural model without significant performance drop. |
| Outcome: | The proposed model can significantly compress a large model without significant performance drop. |
Multi-task Learning for Automated Essay Scoring with Sentiment Analysis (2020.aacl-srw)
Copied to clipboard
| Challenge: | Automated Essay Scoring (AES) is a process that aims to alleviate the workload of graders and improve the feedback cycle in educational systems. |
| Approach: | They propose to combine two tasks, sentiment analysis and AES by utilizing multi-task learning to combine sentiment features extracted from opinion expressions. |
| Outcome: | The proposed model produces a QWK of 0.763 on the Automated StudentAssessment Prize (ASAP) benchmark. |
Designing an Automatic Agent for Repeated Language–based Persuasion Games (2022.tacl-1)
Copied to clipboard
| Challenge: | Existing work on persuasion games assumes communication with stylized messages that do not consist of real-world natural language. |
| Approach: | They propose to use a repeated sender-decision maker game to persuade a receiver to accept a deal by sending one of several possible natural language reviews to the expert. |
| Outcome: | The proposed expert is superior to baselines and adaptable to different decision makers and potential proposed deals. |
Using Snomed to recognize and index chemical and drug mentions. (D19-57)
Copied to clipboard
| Challenge: | a new named entity extraction system is proposed for biological texts . the system is based on machine learning and deep learning . |
| Approach: | They propose a named entity extraction system based on machine learning and deep learning . they propose to map drug names in Spanish biomedical texts using Snomed . |
| Outcome: | The proposed system achieves 78% in the first sub-track and 72% in the second task. |
Mitigating the Burden of Redundant Datasets via Batch-Wise Unique Samples and Frequency-Aware Losses (2023.acl-industry)
Copied to clipboard
Donato Crisostomi, Andrea Caciolai, Alessandro Pedrani, Kay Rottmann, Alessandro Manzotti, Enrico Palumbo, Davide Bernardi
| Challenge: | Existing solutions to train deep learning models on redundant datasets are difficult to implement in industrial settings. |
| Approach: | They propose a method to eliminate duplicates at the batch level without altering the data distribution observed by the model. |
| Outcome: | The proposed approach reduces training times on models on redundant datasets by up to 87% and 46% on average, with a drop in model performance of 0.2% relative at worst. |
Text Extraction and Script Completion in Images of Arabic Script-Based Calligraphy: A Thesis Proposal (2025.naacl-srw)
Copied to clipboard
| Challenge: | despite its artistic elements, Arabic calligraphy is difficult to read, even for those fluent in Arabic. |
| Approach: | They analyze the variability in calligraphic styles and the influence of artistic distortions to improve text extraction and script completion. |
| Outcome: | The proposed methods improve text extraction and script completion in Arabic calligraphy . the authors show that the proposed techniques are more efficient than traditional methods . |
LogiTorch: A PyTorch-based library for logical reasoning on natural language (2022.emnlp-demos)
Copied to clipboard
| Challenge: | Logical reasoning on natural language is one of the most challenging tasks for deep learning models. |
| Approach: | They propose a library that includes logical reasoning benchmarks and models . they use a dataset to run the library or fine tune the models with different hyperparameters . |
| Outcome: | This library includes logical reasoning benchmarks, models, utility functions and co-reference resolution. |
Automatic Detection of Stigmatizing Uses of Psychiatric Terms on Twitter (2022.lrec-1)
Copied to clipboard
| Challenge: | Psychiatry and people suffering from mental disorders have often been given a pejorative label that induces social rejection. |
| Approach: | They propose to use deep learning to detect polarity and type of use in tweets . they propose to combine polarization detection with typeof use detection to improve polarities . |
| Outcome: | The proposed models can detect the polarity of a tweet and the types of use on a dataset that is not yet available. |
DATE: Detecting Anomalies in Text via Self-Supervision of Transformers (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent deep learning methods for anomalies in images learn better features of normality in an end-to-end self-supervised setting. |
| Approach: | They propose to use a novel pretext task to learn a deep learning model for Anomaly Detection in text to train a model to discriminate between different transformations applied to visual data. |
| Outcome: | The proposed method outperforms state-of-the-art methods on 20Newsgroups and AG News datasets in the semi-supervised setting and in the unsupervised setting. |
Relation Embedding with Dihedral Group in Knowledge Graph (P19-1)
Copied to clipboard
| Challenge: | Existing models for link prediction fail to capture relation compositions, resulting in lack of interpretability for reasoning on incomplete knowledge graph (KG). |
| Approach: | They propose a new model that learns knowledge graph embeddings that can capture relation compositions by nature and reduces the solution space drastically. |
| Outcome: | The proposed model outperforms existing models and is comparable to or better than deep learning models such as ConvE. |
Semi-supervised Adversarial Text Generation based on Seq2Seq models (2022.emnlp-industry)
Copied to clipboard
| Challenge: | In contrast, adversarial training has been used in computer vision to improve models’ robustness due to the discrete nature of text. |
| Approach: | They propose a way to generate adversarial samples by using pseudo-labeled in-domain text data to train a seq2seq model for adversarials and combine it with paraphrase detection. |
| Outcome: | The proposed model generates realistic and relevant adversarial samples compared to other state-of-the-art models and recovers up to 70% of errors. |
Neural Arabic Text Diacritization: State of the Art Results and a Novel Approach for Machine Translation (D19-52)
Copied to clipboard
| Challenge: | a number of Arabic text diacritizers use diacritics to convey information about meaning of a word . Arabic text to speech (TTS) requires a complex process to determine the correct diacritical for each character . |
| Approach: | They propose to use Arabic diacritization to enhance machine translation models . they propose to build automatic Arabic text diacritics using two approaches . |
| Outcome: | The proposed models are either better or on par with other models, which require language-dependent post-processing steps, unlike ours. |
SynJax: Structured Probability Distributions for JAX (2023.emnlp-demo)
Copied to clipboard
| Challenge: | a number of deep learning libraries have been developed to account for structured objects . a vectorized implementation of inference algorithms for structured distributions is difficult to implement . |
| Approach: | SynJax provides vectorized implementations of inference algorithms for structured distributions . authors propose to use a vectorized version of the algorithms to model structure in data . similar structures appear in biology and chemistry . |
| Outcome: | SynJax provides an efficient vectorized implementation of inference algorithms for structured distributions. |
RedactOR: An LLM-Powered Framework for Automatic Clinical Data De-Identification (2025.acl-industry)
Copied to clipboard
Praphul Singh, Charlotte Dzialo, Jangwon Kim, Sumana Srivatsa, Irfan Bulu, Sri Gadde, Krishnaram Kenthapadi
| Challenge: | Existing de-identification methods suffer from recall errors, limited generalization, and inefficiencies, limiting their real-world applicability. |
| Approach: | They propose a multi-modal framework for de-identifying electronic health records using a retrieval-based entity relexicalization approach. |
| Outcome: | The proposed framework achieves competitive performance while optimizing token usage to reduce LLM costs. |
ArMATH: a Dataset for Solving Arabic Math Word Problems (2022.lrec-1)
Copied to clipboard
| Challenge: | This paper is the first to use deep learning methods to solve Arabic MWPs . it is also the first study to use transfer learning to solve MWp across different languages . |
| Approach: | They contribute to the first large-scale dataset for Arabic Math Word Problems . they use deep learning methods to solve Arabic MWPs and a transfer learning model to promote performance . |
| Outcome: | The proposed model improves Arabic MWP solvers by 3% over the existing model. |
Fast and Light-Weight Answer Text Retrieval in Dialogue Systems (2022.naacl-industry)
Copied to clipboard
| Challenge: | a recent study shows that text retrieval can be used to find information relevant to user requests. |
| Approach: | They propose to use a corpus of text to search for relevant responses to user requests . they compare this approach to other methods that use intent detection . |
| Outcome: | a new approach can be used to search through a corpus of text to find relevant responses to user requests. |
Contextual Text Denoising with Masked Language Model (D19-55)
Copied to clipboard
| Challenge: | Recent advances in NLP have been vulnerable to noisy inputs. |
| Approach: | They propose a contextual text denoising algorithm based on a ready-to-use masked language model that does not require retraining and can be integrated into any NLP system without additional training on paired cleaning training data. |
| Outcome: | The proposed algorithm can correct noise text and improve performance in several downstream tasks. |
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)
Copied to clipboard
Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang
| Challenge: | Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction. |
| Approach: | They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack. |
| Outcome: | The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses. |
Can Taxonomy Help? Improving Semantic Question Matching using Question Taxonomy (C18-1)
Copied to clipboard
Deepak Gupta, Rajkumar Pujari, Asif Ekbal, Pushpak Bhattacharyya, Anutosh Maitra, Tom Jain, Shubhashis Sengupta
| Challenge: | Existing QA systems that answer factual questions with short answers are rare in practice. |
| Approach: | They propose a proposed two-layered taxonomy technique for semantic question matching . they augment state-of-the-art deep learning models with question classes from a deep learning based question classifier . |
| Outcome: | The proposed technique achieves state-of-the-art on an open-domain dataset. |
Self-Supervised Learning for Pairwise Data Refinement (2020.aacl-main)
Copied to clipboard
| Challenge: | Pairwise data constructed from weakly supervised signals is widely used for training deep learning models. |
| Approach: | They propose two methods to refine pairwise data that are aimed to obtain subsets that are more useful as learning examples. |
| Outcome: | The proposed methods achieve most machine translation gains in the first iteration, but following iterations further improve its intrinsic evaluation. |
Many Faces of Feature Importance: Comparing Built-in and Post-hoc Feature Importance in Text Classification (D19-1)
Copied to clipboard
| Challenge: | Feature importance is commonly used to explain machine predictions . however, the consistency of feature importance via different methods remains understudied . |
| Approach: | They compare feature importance from built-in mechanisms and post-hoc methods that approximate model behavior to find similarities between models. |
| Outcome: | The proposed methods show that features from traditional models are more similar with each other than with deep learning models. |
Systematic Generalization on gSCAN with Language Conditioned Embedding (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing deep learning models fail when the test set is systematically different from the training data. |
| Approach: | They propose a method that explicitly models the relations between objects in their contexts while learning their representations. |
| Outcome: | The proposed model outperforms the baseline model and reaches state-of-the-art performance on grounded SCAN (gSCAN), a grounded natural language navigation dataset. |
On Adversarial Examples for Character-Level Neural Machine Translation (C18-1)
Copied to clipboard
| Challenge: | Using adversarial examples to measure robustness of deep learning models has become a standard procedure due to the difficulty of creating white-box adversarials for discrete text input. |
| Approach: | They propose two novel attacks which aim to remove or change a word in a translation, rather than simply break the NMT. |
| Outcome: | The proposed attacks are significantly stronger than their black-box counterparts in different attack scenarios, showing more serious vulnerabilities than previously known. |
EZ-STANCE: A Large Dataset for Zero-Shot Stance Detection (2023.findings-emnlp)
Copied to clipboard
| Challenge: | EZ-STANCE is a large dataset for zero-shot stance detection in english . it includes both noun-phrase targets and claim targets covering a wide range of domains. |
| Approach: | They present a large English ZSSD dataset with 30,606 annotated text-target pairs . they propose to transform EZ-STANCE into the NLI task by applying two simple yet effective prompts to noun-phrase targets. |
| Outcome: | The proposed dataset includes noun-phrase targets and claim targets covering a wide range of domains. |
Exploring Optimism and Pessimism in Twitter Using Deep Learning (D18-1)
Copied to clipboard
| Challenge: | Identifying optimistic and pessimistic viewpoints and users from Twitter is useful for providing better social support to those who need it. |
| Approach: | They propose deep learning models to predict optimism and pessimism in Twitter . they also show that a sentiment classifier would not be sufficient for predicting optimism and psi . |
| Outcome: | The proposed models outperform traditional machine learning classifiers on optimism and pessimism in Twitter. |
Keyphrase Generation: A Text Summarization Struggle (N19-1)
Copied to clipboard
| Challenge: | Existing methods for keyphrase generation are unable to produce valuable terms that do not appear in the text. |
| Approach: | They propose to consider the keyphrase string as an abstractive summary of the title and the abstract. |
| Outcome: | The proposed method can generate better keyphrases than the existing methods or the unsupervised ones. |
Augmenting Small Data to Classify Contextualized Dialogue Acts for Exploratory Visualization (2020.lrec-1)
Copied to clipboard
| Challenge: | a new corpus of conversations is being developed to support data visualization exploration . we use data augmentation to improve our methods for dialogue act classification . |
| Approach: | They propose to use a corpus of conversations to annotate contextualized dialogue acts . they highlight how thinking aloud affects interpretation of dialogue acts in the context . |
| Outcome: | The proposed AI can support visualization exploration with a small corpus of conversations . the proposed AI outperforms existing models in terms of performance and performance . |
Linguistically Motivated Features for Classifying Shorter Text into Fiction and Non-Fiction Genre (2022.coling-1)
Copied to clipboard
| Challenge: | linguistically motivated features are used to classify paragraph-level text into fiction and non-fiction genres. |
| Approach: | They deploy linguistically motivated features to classify paragraph-level text into fiction and non-fiction genres using a logistic regression model. |
| Outcome: | The proposed model gives 15.56% accuracy jump over baseline model . the proposed model also transfers over to another dataset, Baby BNC corpus . |
Clinical Contradiction Detection (2023.emnlp-main)
Copied to clipboard
| Challenge: | Detecting contradictions in text is difficult since it requires clinical expertise. |
| Approach: | They propose to use a medical ontology to build a seed of potential medical contradictions in medical abstracts by distant supervision. |
| Outcome: | The proposed method weakly supervises state-of-the-art deep learning models and shows significant improvements across multiple medical contradiction datasets. |
Explaining Classes through Stable Word Attributions (2022.findings-acl)
Copied to clipboard
| Challenge: | Input saliency methods have become popular for explaining predictions of deep learning models, but there has been little work investigating methods for aggregating prediction-level explanations to the class level. |
| Approach: | They propose a method to aggregate prediction-level explanations to the class level using XLM-R and Integrated Gradients input attribution methods. |
| Outcome: | The proposed method extracts keyword lists of classes from text classification tasks and evaluates them on web register data. |
Robust Task-Oriented Dialogue Generation with Contrastive Pre-training and Adversarial Filtering (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Task-oriented dialogue models can learn non-transferable generalizations by using shortcuts in the data. |
| Approach: | They propose a contrastive learning framework to encourage models to ignore cues and focus on generalisable patterns. |
| Outcome: | The proposed framework performs exceptionally well on task-oriented dialogue datasets. |
Simple and Effective Semi-Supervised Question Answering (N18-2)
Copied to clipboard
| Challenge: | Existing deep learning systems for extractive Question Answering are limited and expensive to construct. |
| Approach: | They propose a semi-supervised QA system where end user specifies a set of documents and only a few labelled examples. |
| Outcome: | The proposed system achieves 50% F1 score on SQuAD and TriviaQA with very little labeled data. |
ESTeR: Combining Word Co-occurrences and Word Associations for Unsupervised Emotion Detection (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies list as many as 154 human emotions, but most researchers agree on basic emotions such as anger, fear, disgust, sadness, surprise, and happiness. |
| Approach: | They propose an unsupervised model for identifying emotions using a novel similarity function based on random walks on graphs. |
| Outcome: | The proposed model can be computed efficiently and avoids dependence on labeled datasets. |
Shorten the Long Tail for Rare Entity and Event Extraction (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing approaches for the long-tailed learning problem seek to manipulate the training data by re-balancing, augmentation or introducing extra prior knowledge. |
| Approach: | They propose to transform infrequent candidate mention representation with the average mention representation in the training dataset to handle the generalization challenge. |
| Outcome: | The proposed framework can generalize to rare or unseen expressions of entities or events, especially for rare types without sufficient training examples. |
A Comprehensive Survey of Sentence Representations: From the BERT Epoch to the CHATGPT Era and Beyond (2024.eacl-long)
Copied to clipboard
Abhinav Ramesh Kashyap, Thanh-Tung Nguyen, Viktor Schlegel, Stefan Winkler, See-Kiong Ng, Soujanya Poria
| Challenge: | Sentence representations are a critical component in NLP applications such as retrieval, question answering, and text classification. |
| Approach: | They present a systematic review of the literature on sentence representations focusing mostly on deep learning models. |
| Outcome: | The proposed methods highlight the key contributions and challenges in this area and suggest potential avenues for improving the quality and efficiency of sentence representations. |
Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoders (2021.acl-short)
Copied to clipboard
| Challenge: | Existing methods to learn prerequisite relations between concepts require annotated concept pairs during training. |
| Approach: | They propose to use an optimized variational graph autoencoder to learn prerequisite chains in unsupervised manner using an information-rich domain and an information poor domain. |
| Outcome: | The proposed model learns to transfer concept prerequisite relations from an information-rich domain (source domain) to an information poor domain (target domain) the annotated data and resources as well as the code will be made publicly available. |
Surgical Feature-Space Decomposition of LLMs: Why, When and How? (2024.acl-long)
Copied to clipboard
| Challenge: | Low-rank approximations of the weight and feature space can enhance the performance of large language models. |
| Approach: | They propose to use weight and feature space decomposition to improve LLM performance . they also extend their investigation to the implications of low-rank approximations on model bias . |
| Outcome: | The proposed low-rank approximations can improve performance of large language models . the authors show that the approximate can improve generalization and inference performance . |
Doc2Bot: Accessing Heterogeneous Documents via Conversational Bots (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Documents contain various structures that hinder the ability of machines to comprehend . user information needs are often underspecified, and the nature of heterogeneous documents poses challenges. |
| Approach: | They propose a dataset for building machines that help users seek information via conversations . their dataset contains over 100,000 turns based on Chinese documents from five domains . |
| Outcome: | The proposed tasks are challenging and worthy of further research. |
Cross-Topic Rumor Detection using Topic-Mixtures (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing work on rumor detection models has explored network structures, propagation paths, user credibility and fusion of heterogeneous data. |
| Approach: | They propose a method that adapts a rumor detection model trained on source to target topics to make rumour predictions. |
| Outcome: | The proposed method outperforms baseline debiasing methods in a cross-topic setting. |
FreeTalky: Don’t Be Afraid! Conversations Made Easier by a Humanoid Robot using Persona-based Dialogue (2022.lrec-1)
Copied to clipboard
| Challenge: | FreeTalky is a deep learning-based foreign language learning platform for people who experience anxiety dealing with foreign languages. |
| Approach: | They propose a deep learning-based foreign language learning platform called FreeTalky . it employs a humanoid robot NAO and various deep learning models . |
| Outcome: | The proposed system provides personalized learning based on persona dialogue and grammar error correction, and also helps alleviate xenoglossophobia by replacing the real human in the conversation with a NAO robot, through human evaluation. |
Are Your Keywords Like My Queries? A Corpus-Wide Evaluation of Keyword Extractors with Real Searches (2025.coling-main)
Copied to clipboard
| Challenge: | Keyword Extraction (KE) is essential in Natural Language Processing (NLP) for identifying key terms that represent the main themes of a text. |
| Approach: | They propose to use real query data from Google Trends to evaluate keywords extracted from a text to capture users' top queries. |
| Outcome: | The proposed method can be used with both supervised and unsupervised KE approaches and shows that KeyBERT is the most effective in capturing users’ top queries. |
Even the Simplest Baseline Needs Careful Re-investigation: A Case Study on XML-CNN (2022.naacl-main)
Copied to clipboard
| Challenge: | XML-CNN has been a popular research topic in NLP due to its superior performance . however, the increasing complexity brings difficulties to ensure the true architectural progress . |
| Approach: | They propose to re-examine an influential multi-label text classification method . they propose suitable baselines for multi-level text classification tasks . |
| Outcome: | The proposed method performs better than the original model, the authors show . they show that the re-implementation reveals contradictory results to the original work . |
Stigma Annotation Scheme and Stigmatized Language Detection in Health-Care Discussions on Social Media (2020.lrec-1)
Copied to clipboard
| Challenge: | a large amount of research has been done on the interpretation and influence of stigma on human behaviour and health. |
| Approach: | They develop an annotation scheme and improve the annotation process for stigma identification . they aim to distinguish stigmatised language from non-stigmatised using machine learning and NLP . |
| Outcome: | The proposed method improves the annotation process for stigma identification . the results show that the method performs better than other models . |
A Trusted Multi-View Evidential Fusion Framework for Commonsense Reasoning (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing models that provide evidence for commonsense reasoning tasks have limitations . evidence is often interpreted in ways that are not directly available in the input. |
| Approach: | They propose a trusted multi-view evidential fusion framework that assesses the confidence of evidence and combines different views in a trustworthy manner. |
| Outcome: | The proposed framework can reason with multi-view evidence and compete with state-of-the-art models. |
A Real-World Data Resource of Complex Sensitive Sentences Based on Documents from the Monsanto Trial (2020.lrec-1)
Copied to clipboard
| Challenge: | Sensitive information detection is of great importance in a number of applications where unintended leaks of sensitive information may incur severe negative consequences. |
| Approach: | They propose to use a corpus of sentences to evaluate sensitive information detection approaches . they employ human annotations and automatically infer labels from domain experts . |
| Outcome: | The proposed models are based on a monsanto trial and are evaluated on sentence level. |
Ranking-Constrained Learning with Rationales for Text Classification (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to text classification use labels and rationales as ranking constraints. |
| Approach: | They propose a ranking-constrained loss function that combines cross-entropy loss with ranking losses as rationale constraints to speed up deep learning models with limited training data. |
| Outcome: | The proposed approach outperforms baselines on three human-annotated datasets and shows that it is more efficient than existing approaches. |
Continual Learning Long Short Term Memory (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to prevent catastrophic forgetting in neural networks are based on the stability-plasticity dilemma, but only a limited size of old data is available. |
| Approach: | They propose a Continual Learning Long Short Term Memory cell in Recurrent Neural Network (RNN) that considers the state of each individual task's output gates and the correlation of the states between tasks. |
| Outcome: | The proposed method significantly improves on spoken language understanding tasks over state-of-the-art approaches. |
Habibi - a multi Dialect multi National Arabic Song Lyrics Corpus (2020.lrec-1)
Copied to clipboard
| Challenge: | Unlike western music, Arabic songs are poorly classified and the majority of the songs available online are classified under Modern Arabic Pop genre or what is now known as Franco-Arabic . |
| Approach: | They introduce Habibi the first Arabic Song Lyrics corpus for singers from 18 different Arabic countries. |
| Outcome: | The proposed corpus contains more than 30,000 Arabic song lyrics in 6 Arabic dialects for singers from 18 different arab countries. |
Genre Identification and the Compositional Effect of Genre in Literature (C18-1)
Copied to clipboard
| Challenge: | Literature is artistic and conveys complex themes over the course of very long narratives. |
| Approach: | They propose a method which can work with large literary corpus of texts . they propose 'gutenberg' dataset to perform Genre Identification . |
| Outcome: | The proposed methods improve results in a literature-based task with 200,000 words of literature . the Gutenberg dataset is used to model literary classifications with a high level of fidelity . |
On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations (2022.findings-naacl)
Copied to clipboard
| Challenge: | Recent work shows that deep learning models are sensitive to low-level correlations between simple features and specific output labels, leading to over-fitting and lack of generalization. |
| Approach: | They propose to eliminate single-word correlations altogether to mitigate this problem . they highlight several alternatives to dataset balancing to enhance contexts . |
| Outcome: | The proposed approach to balancing datasets is insufficient, the authors argue . they suggest enhancing datasets with richer contexts and abstaining from interaction . |
Changing the World by Changing the Data (2021.acl-long)
Copied to clipboard
| Challenge: | a new paper argues that data curation is already happening, and it is changing the world . social biases and spurious patterns are attracting more attention in NLP models . |
| Approach: | They argue that data curation is already happening and will be happening . they argue that social biases and spurious patterns are the main problems . |
| Outcome: | a new paper argues that data curation is already and will be happening, and it is changing the world. |
Did the Model Understand the Question? (P18-1)
Copied to clipboard
| Challenge: | Using the notion of “attribution,” deep learning models often ignore important question terms. |
| Approach: | They propose techniques to analyze the sensitivity of a deep learning model to question words . they use attribution to generate adversarial questions using visual and tabular questions . |
| Outcome: | The proposed techniques reduce the accuracy of a visual question answering model by 61.1% and that of 'tabular' question answering models by 3.3%. |
A Novel Perspective to Look At Attention: Bi-level Attention-based Explainable Topic Modeling for News Classification (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing deep learning models have the attention mechanism to improve performance, but the inherent characteristics of deep learning model complexity and the flexibility of the attention structure make them difficult to explain. |
| Approach: | They propose a two-tier attention architecture to decouple the complexity of explanation and the decision-making process by using large-scale news corpora. |
| Outcome: | The proposed model can achieve competitive performance with state-of-the-art models and illustrates its appropriateness from an explainability perspective. |
Negative Training for Neural Dialogue Response Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing models have undesirable generation behaviors, such as generic (boring) responses. |
| Approach: | They propose a framework to minimize undesirable generation behaviors in deep learning models . they use generated samples to feed negative training signals to fine-tune the model . |
| Outcome: | The proposed framework reduces the hit rate of malicious responses or discourages frequent responses and improves response diversity. |
Tweet Stance Detection Using an Attention based Neural Ensemble Model (N19-1)
Copied to clipboard
| Challenge: | Existing deep learning approaches to stance detection in twitter are inadequate to deal with the vanishing-gradient and overfitting problems. |
| Approach: | They propose a neural ensemble model that adopts strengths of two LSTM variants to learn better long-term dependencies. |
| Outcome: | The proposed model improves on the existing deep learning models on single and multi-target stance detection datasets. |
Evaluation of Deep Gaussian Processes for Text Classification (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing models for text classification are limited by the expressability limit and require enormous empirical efforts to come up with a robust model architecture. |
| Approach: | They propose a Bayesian non-parametric Bayessian nonparametric model with strong function compositionality for the task of Text Classification. |
| Outcome: | The proposed models outperform shallow and deep Gaussian processes on the TREC (Text REtrieval Conference) datasets. |
Extracting Chemical-Protein Interactions via Calibrated Deep Neural Network and Self-training (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Several natural language processing methods have been used to extract interactions between chemicals and proteins from biomedical text data. |
| Approach: | They propose a method to extract chemical–protein interactions from biomedical text data . they use a pre-trained language-understanding model and calibration techniques to estimate uncertainty . |
| Outcome: | The proposed approach achieves state-of-the-art performance on the Biocreative VI ChemProt task while preserving higher calibration abilities. |
Who is Killed by Police: Introducing Supervised Attention for Hierarchical LSTMs (C18-1)
Copied to clipboard
| Challenge: | Existing methods to identify police killings from text have not been applied to this problem . et al., 2017: finding names of people killed by police is a critical problem despite public attention . |
| Approach: | They propose a method to deal with multiple appearances of police names in documents . they propose hierarchical LSTMs to model multiple sentences that contain names of interests . |
| Outcome: | The proposed method yields state-of-the-art performance for police killing detection . it relies on hierarchical LSTMs to model the multiple sentences that contain the person names of interests . |
CEASE, a Corpus of Emotion Annotated Suicide notes in English (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing studies on suicide notes have not explored the topic of emotion detection. |
| Approach: | They develop a fine-grained emotion annotated corpus of suicide notes in English and use it to perform emotion detection on a curated dataset. |
| Outcome: | The proposed model performs emotion detection on a curated dataset of 205 suicide notes in English. |
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. |
Content Selection in Deep Learning Models of Summarization (D18-1)
Copied to clipboard
| Challenge: | Using deep learning models, we find that word embedding does not improve performance over simpler models. |
| Approach: | They propose to use sentence embedding to perform content selection across multiple domains . they propose to propose two alternative models that use auto-regressive sentence extraction . |
| Outcome: | The proposed models improve performance across news, personal stories, meetings, and medical articles. |
DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling (2021.emnlp-main)
Copied to clipboard
Baojun Wang, Zhao Zhang, Kun Xu, Guang-Yuan Hao, Yuyang Zhang, Lifeng Shang, Linlin Li, Xiao Chen, Xin Jiang, Qun Liu
| Challenge: | Existing approaches to integrate lexical knowledge into deep learning models are limited by large-scale dynamic lexicons. |
| Approach: | They propose a plug-in lexicon incorporation approach for BERT based sequence labeling tasks . they adopt word-agnostic tag embeddings to avoid re-training the representation . |
| Outcome: | The proposed framework achieves new SOTA even with large scale lexicons, the authors show . they adopt word-agnostic tag embeddings to avoid re-training the representation . |
Private Language Models via Truncated Laplacian Mechanism (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for word embedding are prone to privacy leakage, resulting in weaker relaxations of DP that are inferior to the canonical DP in terms of privacy strength. |
| Approach: | They propose a method for private word embedding that uses a non-trivial extension of the truncated Laplacian mechanism and propose to test its effectiveness. |
| Outcome: | The proposed method has lower variance compared to the previous methods. |
WIKIR: A Python Toolkit for Building a Large-scale Wikipedia-based English Information Retrieval Dataset (2020.lrec-1)
Copied to clipboard
| Challenge: | ad-hoc information retrieval methods usually require large amounts of annotated data to be effective. |
| Approach: | They propose an open-source toolkit to automatically build large-scale English information retrieval datasets based on Wikipedia. |
| Outcome: | The proposed toolkit builds large-scale English information retrieval datasets based on Wikipedia with 59,252 queries and 2,617,003 pairs. |
Posterior Control of Blackbox Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for conditional natural language generation are limited in their ability to produce controlled output. |
| Approach: | They propose to augment neural generation models with discrete control states learned through a structured latent-variable approach. |
| Outcome: | The proposed approach improves over benchmarks while providing fine-grained control. |
On the Use of Bert for Automated Essay Scoring: Joint Learning of Multi-Scale Essay Representation (2022.naacl-main)
Copied to clipboard
| Challenge: | Pre-trained models have not been used to outperform other deep learning models such as CNN in Automated Essay Scoring (AES). |
| Approach: | They propose a novel multi-scale essay representation for BERT that can be jointly learned . they employ multiple losses and transfer learning from out-of-domain essays to further improve performance . |
| Outcome: | The proposed model outperforms existing models in the area of automated essay scoring . the proposed model generalizes well to the CommonLit Readability Prize data set . |
Context-aware Information-theoretic Causal De-biasing for Interactive Sequence Labeling (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing deep learning models for sequence labeling are expensive and time-consuming. |
| Approach: | They propose an interactive sequence labeling that allows training directly with the user feedback . they identify context and feedback biases by formulating interactive sequence labels via a Structural Causal Model. |
| Outcome: | The proposed approach can effectively alleviate the biases and can be learnt with the user feedback. |
End-to-end Case-Based Reasoning for Commonsense Knowledge Base Completion (2023.eacl-main)
Copied to clipboard
| Challenge: | Pretrained language models have been shown to store knowledge in their parameters and have achieved reasonable performance in knowledge-intensive tasks. |
| Approach: | They propose to provide retrieved passages that contain relevant knowledge as additional input to the commonsense knowledge base completion (CKBC) task. |
| Outcome: | The proposed framework generates more valid, informative, and novel knowledge than the state-of-the-art COMET model for commonsense knowledge base completion (CKBC) tasks. |
EmpathBERT: A BERT-based Framework for Demographic-aware Empathy Prediction (2021.eacl-main)
Copied to clipboard
| Challenge: | EmpathBERT is a demographic-aware framework for empathy prediction based on BERT. |
| Approach: | They propose a demographic-aware framework for empathy prediction based on BERT and utilize user demographics to analyze user responses to stimulative news articles. |
| Outcome: | The proposed framework surpasses machine learning and deep learning models and highlights the importance of demographic information in the responses. |
Is Attention Explanation? An Introduction to the Debate (2022.acl-long)
Copied to clipboard
Adrien Bibal, Rémi Cardon, David Alfter, Rodrigo Wilkens, Xiaoou Wang, Thomas François, Patrick Watrin
| Challenge: | Attention has been used in various tasks of NLP and other fields of machine learning to increase performance and provide some explanations. |
| Approach: | They propose to use attention as an explanation for deep learning models to increase performance . they propose to apply attention weights to queries and queries based on scalar scores . |
| Outcome: | The proposed model can be used to increase performance while providing some explanations. |
Graph Convolutional Networks for Event Causality Identification with Rich Document-level Structures (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing models for document-level Event Causality Identification (ECI) are limited to intra-sentence contexts where event mention pairs are presented in the same sentences. |
| Approach: | They propose a deep learning model that accepts inter-sentence event mention pairs . they use interaction graphs to capture relevant connections between important objects . |
| Outcome: | The proposed model achieves state-of-the-art on two benchmark datasets. |
Evidence-based Fact-Checking of Health-related Claims (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evidence-based factchecking datasets contain synthetic claims and lack real-world verification. |
| Approach: | They propose a dataset for evidence-based fact-checking of health-related claims that evaluates their truthfulness against scientific articles. |
| Outcome: | The proposed dataset evaluates real-world claims against scientific articles. |
Towards Intention Understanding in Suicidal Risk Assessment with Natural Language Processing (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Suicide is a global problem, with one suicide case for every 100 deaths worldwide . social networking sites are an essential forum for communication and information sharing . |
| Approach: | This paper compares natural language processing to suicidal ideation detection and risk assessment . it urges better intention understanding for reliable suicide risk assessment with computational methods . |
| Outcome: | This paper compares the performance of natural language processing to suicidal ideation detection and risk assessment tasks. |
Concadia: Towards Image-Based Text Generation with a Purpose (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing models fail to generate fluent, truthful text, despite excellent results on benchmark datasets . current systems fail to produce texts that are useful in practice, authors argue . |
| Approach: | They propose to distinguish descriptions from captions based on their communicative roles . descriptions focus on visual features and are meant to replace an image . authors characterize commonalities and differences between descriptions and captions in a Wikipedia corpus . |
| Outcome: | The proposed model can generate fluent, truthful texts in a wide range of scenarios . it can also generate captions that are used to make an image accessible to users who can't see them . |
Word Segmentation by Separation Inference for East Asian Languages (2022.findings-acl)
Copied to clipboard
| Challenge: | Chinese Word Segmentation (CWS) is a sequence labeling task that divides sentences into words . despite diverse tagging schemas, they all carry implicit position information. |
| Approach: | They propose to model the separation state of every two consecutive characters by tagging them as two tags. |
| Outcome: | The proposed framework outperforms state-of-the-art on Japanese and Korean Word Segmentation datasets. |
Evaluating the Utility of Hand-crafted Features in Sequence Labelling (D18-1)
Copied to clipboard
| Challenge: | Conventional wisdom is that hand-crafted features are redundant for deep learning models . authors propose a method for using handcrafted features in a hybrid learning approach . |
| Approach: | They propose a method for exploiting handcrafted features as part of a hybrid learning approach. |
| Outcome: | The proposed method outperforms baseline models on a named entity recognition task and reduces training requirements to 60% while maintaining the same predictive accuracy. |
VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of Transformations (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for detecting adversarial attacks need original/adversarial data. |
| Approach: | They propose to detect adversarial text by voting on hard labels from predictions of transformations using a model that uses original/adversarial data. |
| Outcome: | The proposed method detects adversarial text across various state-of-the-art attacks, models, and datasets without training. |
Graph Transformer Networks with Syntactic and Semantic Structures for Event Argument Extraction (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models for Event Argument Extraction fail to exploit semantic structures of sentences to induce effective representations for EAE. |
| Approach: | They propose a novel model that exploits syntactic and semantic structures of sentences to learn more effective sentence structures for EAE. |
| Outcome: | The proposed model improves the performance of the existing models on standard datasets. |
Multi-task Learning to Enable Location Mention Identification in the Early Hours of a Crisis Event (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Social media is a platform for people to share their concerns and report information as eyewitnesses of events. |
| Approach: | They propose a multi-task learning approach to leverage available annotated data for several related tasks from the crisis domain to improve performance on a main task with limited annotation. |
| Outcome: | The proposed approach improves performance on a task with limited annotated data. |
Multi-Aspect Transfer Learning for Detecting Low Resource Mental Disorders on Social Media (2022.lrec-1)
Copied to clipboard
| Challenge: | Mental disorders are an important and pervasive public health issue. |
| Approach: | They propose to use linguistic features to improve mental disorder detection . they propose to apply multi-aspect transfer learning to detecting disorders from social media . |
| Outcome: | The proposed methods can be used to improve mental disorder detection in the context of data scarcity and understanding the overlapping symptoms between disorders. |
Ad-hoc Document Retrieval using Weak-Supervision with BERT and GPT2 (2020.emnlp-main)
Copied to clipboard
| Challenge: | a weakly-supervised method is used for document retrieval tasks . traditional methods are used for ad-hoc querying, but they require large amounts of labeled data . |
| Approach: | They propose a weakly-supervised method for training deep learning models for ad-hoc document retrieval using weak-supervision from the documents in the corpus. |
| Outcome: | The proposed method outperforms state-of-the-art methods on a COVID-19 dataset and two news datasets without the need for labeling data. |
NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing question answering datasets lack numerical reasoning and reasoning processes . current research on numerical reasoning focuses on simple calculations . |
| Approach: | They propose a conversational and bilingual question answering dataset with numerical reasoning with compound mathematical expressions. |
| Outcome: | The proposed model achieves 55.5 exact match scores while human performance is 89.7. |
Leveraging Training Dynamics and Self-Training for Text Classification (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Semi-supervised learning (SSL) is a promising technique for improving deep learning models when training data is scarce. |
| Approach: | They propose a semi-supervised learning approach that leverages training dynamics of unlabeled data. |
| Outcome: | The proposed method achieves an average increase in F1 score of 3.5% over baselines in low resource settings. |
Learning to Infer from Unlabeled Data: A Semi-supervised Learning Approach for Robust Natural Language Inference (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Semi-supervised learning (SSL) is a popular technique for reducing the reliance on human annotations for NLI tasks. |
| Approach: | They propose a way to incorporate unlabeled data into semi-supervised learning (SSL) using a conditional language model, they propose to generate hypotheses for unlabed sentences . |
| Outcome: | The proposed framework significantly improves the performance of four NLI datasets in low-resource settings. |
Federated Continual Learning for Text Classification via Selective Inter-client Transfer (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Continual Learning (CL) is a privacy-preserving machine learning technique that enables collaborative training of ML models by sharing model parameters across distributed clients. |
| Approach: | They propose a framework which selectively combines model parameters of foreign clients to maximize knowledge transfer while preserving privacy. |
| Outcome: | The proposed framework improves the performance of a text classification task using five datasets from diverse domains while preserving privacy. |
Content Explorer: Recommending Novel Entities for a Document Writer (D18-1)
Copied to clipboard
| Challenge: | Existing tools for exploratory search can be useful for document writers but they are not always effective for identifying topics for further research. |
| Approach: | They propose a supervised learning problem for recommending topics to a writer . they propose entropy loss function modification to improve the results . |
| Outcome: | The proposed model improves on a large dataset and can be used to identify topics for further research. |
Exploiting Document Structures and Cluster Consistencies for Event Coreference Resolution (2021.acl-long)
Copied to clipboard
| Challenge: | Existing deep learning models for event coreference resolution are limited in that they cannot exploit important interactions between relevant objects for ECR. |
| Approach: | They propose a deep learning model that groups coreferent event mentions into the same clusters . they use document structures to capture relevant objects for ECR . |
| Outcome: | The proposed model achieves state-of-the-art on two benchmark datasets. |
OTSeq2Set: An Optimal Transport Enhanced Sequence-to-Set Model for Extreme Multi-label Text Classification (2022.emnlp-main)
Copied to clipboard
| Challenge: | Extreme multi-label text classification (XMTC) is a task of finding the most relevant subset labels from an extremely large label set. |
| Approach: | They propose an autoregressive sequence-to-set model for XMTC tasks named OTSeq2Set. |
| Outcome: | The proposed model outperforms other competitive baselines on 4 benchmark datasets. |
LayoutReader: Pre-training of Text and Layout for Reading Order Detection (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for reading order detection are too laborious to annotate large datasets. |
| Approach: | They propose to use a large-scale dataset to annotate reading order information for document images . they use XML metadata to capture the reading order of WORD documents . |
| Outcome: | The proposed model performs almost perfectly in reading order detection and improves both open-source and commercial OCR engines in ordering text lines in their results. |
CitRet: A Hybrid Model for Cited Text Span Retrieval (2022.coling-1)
Copied to clipboard
| Challenge: | Current methods for citing text span retrieval (CTSR) rely on pre-trained off-the-shelf deep learning models like SciBERT. |
| Approach: | They propose a hybrid model for cited text span retrieval that leverages unique semantic and syntactic structural characteristics of scientific documents. |
| Outcome: | The proposed model improves state-of-the-art by 15% on the CLSciSumm shared tasks. |
Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation (2020.findings-emnlp)
Copied to clipboard
Amir Pouran Ben Veyseh, Nasim Nouri, Franck Dernoncourt, Quan Hung Tran, Dejing Dou, Thien Huu Nguyen
| Challenge: | Aspect-based Sentiment Analysis (ABSA) seeks to predict sentiment polarity of input sentences toward a specific aspect. |
| Approach: | They propose a graph-based deep learning model that integrates dependency trees into deep learning models to improve ABSA performance. |
| Outcome: | The proposed model achieves state-of-the-art on three benchmark datasets. |
Logic Traps in Evaluating Attribution Scores (2022.acl-long)
Copied to clipboard
| Challenge: | Modern deep learning models are notoriously opaque, which has motivated the development of methods for interpreting how deep models predict. |
| Approach: | They propose to review existing methods for evaluating attribution scores and summarize the logic traps in these methods. |
| Outcome: | The proposed methods show that they do not contain logic traps and that they are not reliable. |
CLeVeR: Multi-modal Contrastive Learning for Vulnerability Code Representation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for detecting code capture the overall semantics of the code rather than its intrinsic vulnerability-specific semantics. |
| Approach: | They propose an approach that leverages contrastive learning to generate precise vulnerability code representations under the supervision of vulnerability descriptions. |
| Outcome: | The proposed approach outperforms state-of-the-art methods in vulnerability detection tasks by 11.85% and 13.61%. |
Auditing Deep Learning processes through Kernel-based Explanatory Models (D19-1)
Copied to clipboard
| Challenge: | Existing nonlinearity of deep learning models can be a major drawback . ethical accountability of such systems is becoming a crucial issue . |
| Approach: | They propose to use Layerwise Relevance Propagation to trace back connections between linguistic properties of input instances and system decisions. |
| Outcome: | The proposed model evaluates the transparency and coherence of analogy-based explanations modeling an audit stage for the system. |
MDACE: MIMIC Documents Annotated with Code Evidence (2023.acl-long)
Copied to clipboard
Hua Cheng, Rana Jafari, April Russell, Russell Klopfer, Edmond Lu, Benjamin Striner, Matthew Gormley
| Challenge: | Computer-Assisted Coding (CAC) systems are required to provide supporting textual evidence to justify billing codes. |
| Approach: | They propose a dataset for evidence/rationale extraction on an extreme multi-label classification task over long medical documents. |
| Outcome: | The proposed dataset can be used to evaluate evidence extraction methods for CAC systems, as well as the accuracy and interpretability of deep learning models for multi-label classification. |
Human Attention Maps for Text Classification: Do Humans and Neural Networks Focus on the Same Words? (2020.acl-main)
Copied to clipboard
| Challenge: | Attention-based models have been claimed to add interpretability, but little is known about the actual relationships between machine and human attention. |
| Approach: | They conduct the first quantitative assessment of human versus computational attention mechanisms for the text classification task. |
| Outcome: | The proposed models are compared against machine attention maps on a publicly available YELP dataset. |
De-Confounded Variational Encoder-Decoder for Logical Table-to-Text Generation (2021.acl-long)
Copied to clipboard
| Challenge: | Logical table-to-text generation is challenging where deep learning models capture surface-level spurious correlations rather than the causal relationships between the table x and the sentence y. |
| Approach: | They propose to use variational inference to estimate the confounders in the latent space and cooperate with the causal intervention based on Pearl’s do-calculus to alleviate the spurious correlations. |
| Outcome: | The proposed model outperforms baselines and achieves new state-of-the-art performance on two logical table-to-text datasets in terms of logical fidelity. |
Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances in natural language processing have highlighted the vulnerability of deep learning models to adversarial attacks. |
| Approach: | They propose a benchmark for textual adversarial defence that evaluates state-of-the-art defence mechanisms across diverse datasets, models, and tasks. |
| Outcome: | The proposed benchmark incorporates a wide range of datasets and evaluates state-of-the-art defence mechanisms. |
Introducing a New Dataset for Event Detection in Cybersecurity Texts (2020.emnlp-main)
Copied to clipboard
| Challenge: | a large amount of text data is produced to report and discuss cyber vulnerabilities . detecting cybersecurity events is necessary to keep us informed about the fast growing number of such events reported in text. |
| Approach: | They propose a dataset characterizing the manual annotation for 30 important cybersecurity event types and a large dataset to develop deep learning models. |
| Outcome: | The proposed dataset characterizes the manual annotation for 30 important event types and supports the modeling of document-level information to improve the performance. |
An Empirical Study of Memorization in NLP (2022.acl-long)
Copied to clipboard
| Challenge: | Existing studies see memorization as hindering generalization in deep learning models. |
| Approach: | They propose a long-tail theory to explain the memorization behavior of deep learning models . they use three different NLP tasks to test whether the theory holds . |
| Outcome: | The proposed long-tail theory is validated in three NLP tasks and shows it is faithful. |
MOSAICo: a Multilingual Open-text Semantically Annotated Interlinked Corpus (2024.naacl-long)
Copied to clipboard
Simone Conia, Edoardo Barba, Abelardo Carlos Martinez Lorenzo, Pere-Lluís Huguet Cabot, Riccardo Orlando, Luigi Procopio, Roberto Navigli
| Challenge: | Existing approaches to integrate semantics into Natural Language Understanding (NLP) systems are cost-effective and environmental impact-related. |
| Approach: | They propose to provide semantically-annotated corpora for four NLU tasks across five languages and to drop the requirement of closed datasets. |
| Outcome: | The proposed model provides hundreds of millions of silver yet high-quality annotations for four NLU tasks across five languages. |
Deep Weighted MaxSAT for Aspect-based Opinion Extraction (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing deep learning models lack the capability to encode explicit domain knowledge to model complex causal relationships among variables. |
| Approach: | They propose a model that uses a weighted version of MaxSAT to model logic inference . they propose to use this model to rectify erroneous predictions from deep neural networks . |
| Outcome: | The proposed model combines the benefits of high-level feature learning, knowledge reasoning, and structured learning with observable performance gain for aspect-based opinion extraction. |
PE: A Poincare Explanation Method for Fast Text Hierarchy Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent work on feature interactions neglects underlying linguistic information in feature representations. |
| Approach: | They propose a method for modeling feature interactions with hyperbolic spaces using Poincare Explanation. |
| Outcome: | The proposed method is able to model feature interactions with hyperbolic spaces in a time efficient manner. |
DeepREF: A Framework for Optimized Deep Learning-based Relation Classification (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing frameworks for relation extraction (RE) are limited due to lack of implementation details. |
| Approach: | They propose to use deep learning to develop relation extraction systems using deep learning models. |
| Outcome: | The proposed framework is inspired by the OpenNRE and REflex existing frameworks. |
Exploring Data Augmentation Strategies for Hate Speech Detection in Roman Urdu (2022.lrec-1)
Copied to clipboard
| Challenge: | a number of social media platforms are generating hateful content, a new study finds . augmentation techniques are needed to improve the performance of the models . |
| Approach: | They evaluate different data augmentation techniques for the improvement of hate speech detection in Roman Urdu. |
| Outcome: | The proposed techniques improve hate speech detection in Roman Urdu on two datasets. |
BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers (2024.findings-emnlp)
Copied to clipboard
| Challenge: | *BadFair* is a backdoored fairness attack methodology that discriminates and produces incorrect results for specific groups. |
| Approach: | They propose a backdoored fairness attack methodology that discriminates and produces incorrect results for specific groups. |
| Outcome: | The proposed model achieves 85% success rate in attacks aimed at target groups on average while only incurring a minimal accuracy loss. |
Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions (2020.acl-main)
Copied to clipboard
| Challenge: | Modern deep learning models for NLP are notoriously opaque, and this has motivated efforts to design example-specific approaches to interpret such models. |
| Approach: | They propose to use influence functions to explain models by highlighting important words in input text to provide models with an explanation. |
| Outcome: | The proposed approach is particularly useful for natural language inference, a task in which ‘saliency maps’ may not have clear interpretation. |
LLMs as a synthesis between symbolic and distributed approaches to language (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a fierce battle is being fought between symbolic and distributed approaches to language and cognition . a recent study shows that morphosyntactic knowledge is encoded in a near-discrete fashion in LLMs . |
| Approach: | a new position paper examines the role of distributed and distributed approaches in language learning . authors argue that deep learning models represent a synthesis between the two traditions . |
| Outcome: | a new position paper shows that deep learning models for language represent a synthesis between the two traditions. |
Understanding Deep Learning Performance through an Examination of Test Set Difficulty: A Psychometric Case Study (D18-1)
Copied to clipboard
| Challenge: | Existing methods to evaluate deep learning models that are not considered for test set accuracy are difficult to interpret. |
| Approach: | They examine the impact of a test set question’s difficulty to determine if there is a relationship between difficulty and performance. |
| Outcome: | The proposed model can learn examples of varying difficulty at different rates if it does well on hard examples and poor on easy items because a dataset is all easy, but has "solved" anything? |
Text2Tree: Aligning Text Representation to the Label Tree Hierarchy for Imbalanced Medical Classification (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to medical text classification are struggling with imbalanced data distribution and rare labels. |
| Approach: | They propose a framework-agnostic algorithm that only utilizes internal label hierarchy in training deep learning models. |
| Outcome: | The proposed approach performs better on public datasets and real-world medical records than existing methods. |
Explainable Tsetlin Machine Framework for Fake News Detection with Credibility Score Assessment (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing models for fake news classification are difficult to explain and quality-assure . however, they are black-box-based and lack a clear explanation of their decisions. |
| Approach: | They propose an interpretable fake news detection framework based on the recently introduced Tsetlin Machine (TM) they use conjunctive clauses to capture lexical and semantic properties of both true and fake news text and use clause ensembles to calculate the credibility of fake news. |
| Outcome: | The proposed framework outperforms baseline models on PolitiFact and GossipCop datasets in terms of accuracy and provides higher F1-score than BERT and XLNet, but lower accuracy. |
Human-grounded Evaluations of Explanation Methods for Text Classification (D19-1)
Copied to clipboard
| Challenge: | Explainable Artificial Intelligence (XAI) is aimed at providing explanations for decisions made by AI systems. |
| Approach: | They propose to use model-agnostic and model-specific explanation methods for CNNs for text classification to provide human-grounded evaluations. |
| Outcome: | The proposed methods could be used to explain models' results and improve AIs and humans in many cases. |
Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to augment textual data are limited due to the discrete characteristics of the textual dataset. |
| Approach: | They propose a decision-boundary-aware data augmentation strategy to enhance robustness using pretrained language models by shifting latent features closer to the decision boundary and reconstruction to generate an ambiguous version with a soft label. |
| Outcome: | The proposed method performs better than existing methods and is extensible with curriculum data augmentation. |
Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach (2021.emnlp-main)
Copied to clipboard
Simiao Zuo, Chen Liang, Haoming Jiang, Xiaodong Liu, Pengcheng He, Jianfeng Gao, Weizhu Chen, Tuo Zhao
| Challenge: | Existing approaches to adversarial regularization treat adversarials and defending players equally, which is undesirable because only the defending player contributes to the generalization performance. |
| Approach: | They propose a method which formulates adversarial regularization as a Stackelberg game and induces a competition between a leader and a follower. |
| Outcome: | The proposed method outperforms existing adversarial regularization baselines on a set of machine translation and natural language understanding tasks. |
Main Predicate and Their Arguments as Explanation Signals For Intent Classification (2025.naacl-long)
Copied to clipboard
| Challenge: | Intent classification is crucial for conversational agents, and deep learning models perform well in this area due to the lack of suitable benchmark data. |
| Approach: | They propose a technique to augment text samples from intent classification datasets with word-level explanations by marking main predicates and their arguments as explanation signals. |
| Outcome: | The proposed method augments text samples from intent classification datasets with word-level explanations. |
DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversations (2021.acl-long)
Copied to clipboard
| Challenge: | Recent studies on ERC lack the ability to extract and integrate emotional clues from the conversational context. |
| Approach: | They propose a new model that uses multi-turn reasoning modules to extract and integrate emotional clues from conversational context. |
| Outcome: | The proposed model outperforms existing models on three public benchmark datasets and is highly effective and superior to existing models. |
Hollywood Identity Bias Dataset: A Context Oriented Bias Analysis of Movie Dialogues (2022.lrec-1)
Copied to clipboard
Sandhya Singh, Prapti Roy, Nihar Sahoo, Niteesh Mallela, Himanshu Gupta, Pushpak Bhattacharyya, Milind Savagaonkar, Nidhi Sultan, Roshni Ramnani, Anutosh Maitra, Shubhashis Sengupta
| Challenge: | Movies reflect society and also hold power to transform opinions. |
| Approach: | They propose to annotate movie scripts for identity bias using a dataset that is annotated for gender, race/ethnicity, religion, age, occupation, LGBTQ, and other . |
| Outcome: | The proposed dataset contains dialogue turns annotated for gender, race/ethnicity, religion, age, occupation, LGBTQ, and other, which contains biases like body shaming, personality bias, etc. |
Evaluating Saliency Explanations in NLP by Crowdsourcing (2024.lrec-main)
Copied to clipboard
| Challenge: | a crowdsourced method to evaluate saliency methods in NLP is proposed . saliencies are difficult for humans to understand, and can cause psychological harm . |
| Approach: | They propose a method to evaluate saliency methods in NLP by crowdsourcing . they recruited 800 crowd workers and empirically evaluated seven salience methods . |
| Outcome: | The proposed method evaluates saliency methods on two datasets using crowdsourced data . it shows that the results are comparable to existing methods on NLP and CV fields . |
CARER - ClinicAl Reasoning-Enhanced Representation for Temporal Health Risk Prediction (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing deep learning methods require large datasets to achieve high generalizability. |
| Approach: | They propose a framework that enhances deep learning models with clinical rationales derived from medically proficient Large Language Models. |
| Outcome: | The proposed framework outperforms state-of-the-art models on two tasks using two popular EHR datasets by up to 11.2%. |
Building a Synthetic Biomedical Research Article Citation Linkage Corpus (2022.lrec-1)
Copied to clipboard
| Challenge: | citations are used in scientific publications to support the presented results and to demonstrate the previous discoveries. |
| Approach: | They propose a silver standard corpus and a method to find citation linkages in biomedical research papers using deep learning. |
| Outcome: | The proposed model can locate the text spans in a reference article, given a citing statement, based on semantic similarity. |
Modeling Intra-Relation in Math Word Problems with Different Functional Multi-Head Attentions (P19-1)
Copied to clipboard
| Challenge: | Several deep learning models have been proposed for solving math word problems (MWPs) but their approaches to capturing features are not specifically designed for MWP. |
| Approach: | They propose to use a group attention mechanism to extract global features, quantity-related features, quantities-pair features and question-related feature in MWPs. |
| Outcome: | The proposed approach performs significantly better than previous state-of-the-art methods and boosts performance from 66.9% to 69.5% on Math23K with training-test split, from 65.8% to 66.99% on Math 23K with 5-fold cross-validation and from 69.99% to 76.1% on MAWPS. |
UMUTextStats: A linguistic feature extraction tool for Spanish (2022.lrec-1)
Copied to clipboard
| Challenge: | Feature Engineering is the application of domain knowledge to build efficient machine learning models. |
| Approach: | a team of researchers has developed a linguistic extraction tool for Spanish . the tool uses linguistic features and embeddings to build efficient machine learning models . |
| Outcome: | UMUTextStats is a linguistic extraction tool for Spanish . it has been validated in infodemiology, hate-speech detection, author profiling, authorship verification, humour or irony detection, among others. |
Latent Concept-based Explanation of NLP Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing attempts to explain deep learning models rely on input features, such as the words . however, such explanations are often less informative due to the discrete nature of words and lack of contextual verbosity. |
| Approach: | They propose a method that generates explanations for predictions based on latent concepts . they map the representations of salient input words into the training latent space . |
| Outcome: | The proposed method generates explanations for predictions based on latent concepts . it maps representations of salient input words into training latent space . |
A Survey of Machine Translation Tasks on Nigerian Languages (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing work on machine translation of low-resource African languages is limited . despite advances in machine translation, there is limited work on Nigerian languages . |
| Approach: | They propose to focus on neural machine translation techniques for Nigerian languages . they outline the limitations of machine translation research on the continent . |
| Outcome: | The proposed research on Nigerian languages highlights the limitations of the current state of the art in machine translation. |
Unsupervised Selective Rationalization with Noise Injection (2023.acl-long)
Copied to clipboard
| Challenge: | Unsupervised selective rationalization produces rationales alongside predictions, but does not ensure that the rationale contains a plausible explanation for the prediction. |
| Approach: | They propose a technique that injects noise between a rationale generator and a predictor to limit generation of implausible rationales. |
| Outcome: | The proposed method achieves significant improvements in plausibility and task accuracy over the state-of-the-art models while maintaining or improving model faithfulness. |
CancerEmo: A Dataset for Fine-Grained Emotion Detection (2020.emnlp-main)
Copied to clipboard
| Challenge: | a lack of large annotated datasets hinders emotion detection in the health domain . a recent study shows that online sharing of emotions is beneficial to a patient's progress . |
| Approach: | They propose an emotion dataset annotated with eight fine-grained emotions from an online health community. |
| Outcome: | The proposed model achieves an average F1 of 71% on the cancerEmo dataset . the best model achieve a higher F1 than the previous model, which was improved using domain-specific pre-training. |
Exploiting the Syntax-Model Consistency for Neural Relation Extraction (2020.acl-main)
Copied to clipboard
| Challenge: | Existing deep learning models for Relation Extraction (RE) have limited generalization beyond the syntactic structures of the input sentences. |
| Approach: | They propose a deep learning model that uses dependency trees to extract syntactic importance of words for Relation Extraction. |
| Outcome: | The proposed model outperforms existing models on three RE benchmark datasets. |
Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning (2020.emnlp-main)
Copied to clipboard
| Challenge: | Current deep learning models fail to exploit syntactic information of sentences . proposed model incorporates syntax-based opinion possibility scores and syntaktic connections between the words . |
| Approach: | They propose to incorporate syntactic information of sentences into deep learning models for TOWE . they propose a novel regularization technique to improve the performance of the models . |
| Outcome: | The proposed model achieves state-of-the-art on four benchmark datasets. |
Denoising Rationalization for Multi-hop Fact Verification via Multi-granular Explainer (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing rationalization methods for multi-hop fact verification lack nuanced composition in the evidence, which leads to noise rationalization. |
| Approach: | They propose a method to obtain rationale by completely removing subset of input without compromising verification accuracy. |
| Outcome: | The proposed method outperforms 12 baselines on three multi-hop fact verification datasets. |
C-STANCE: A Large Dataset for Chinese Zero-Shot Stance Detection (2023.acl-long)
Copied to clipboard
| Challenge: | Recent advances in zero-shot stance detection are limited to English and Chinese . stance can provide useful information for important events such as policymaking and presidential elections. |
| Approach: | They present a Chinese dataset for zero-shot stance detection that is the first for ZSSD. |
| Outcome: | The proposed dataset is the first Chinese dataset for zero-shot stance detection. |
Tab2Text - A framework for deep learning with tabular data (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Tabular data is a foundational part of social sciences and is used to fit supervised learning models. |
| Approach: | They propose a technique for transforming tabular data to text data to improve deep learning models for tabular datasets. |
| Outcome: | The proposed technique improves performance of deep learning models for tabular data. |
ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot Filler (2024.lrec-main)
Copied to clipboard
| Challenge: | State-of-the-art intent classification and slot filling methods rely on data-intensive deep learning models . large language models exhibit remarkable zero-shot performance across various natural language tasks. |
| Approach: | They propose an approach framing IC and SF as language generation tasks for instruction-LLMs with a more efficient SF-prompting method. |
| Outcome: | The proposed approach outperforms state-of-the-art IC+SF method and in-context learning methods with GPT3.5 (175B). |
NILE : Natural Language Inference with Faithful Natural Language Explanations (2020.acl-main)
Copied to clipboard
| Challenge: | Recent growth in popularity of deep learning models on NLP classification tasks has accompanied the need for generating some form of natural language explanation of predicted labels. |
| Approach: | They propose a novel method which generates labels along with its faithful explanations. |
| Outcome: | The proposed method is more accurate than previously reported methods and has higher sensitivity than previous methods. |
Towards Robustifying NLI Models Against Lexical Dataset Biases (2020.acl-main)
Copied to clipboard
| Challenge: | Recent studies show that deep learning models exploit dataset biases without deep understanding of the language semantics. |
| Approach: | They propose two methods to debiase models against lexical dataset biases . they use contradiction-word bias and word-overlapping bias as examples . |
| Outcome: | The proposed method removes label bias at embedding level, while the other uses a bag-of-words sub-model to capture features likely to exploit the bias. |
Identification of Fine-Grained Location Mentions in Crisis Tweets (2022.lrec-1)
Copied to clipboard
| Challenge: | Recent studies have focused on identifying informative tweets by individuals affected by a crisis, without considering their specific types. |
| Approach: | They assemble two tweet crisis datasets and manually annotate them with specific location types to facilitate progress on the fine-grained location identification task. |
| Outcome: | The proposed model performs well in both in-domain and cross-domain settings. |
AUTOSUMM: Automatic Model Creation for Text Summarization (2021.emnlp-main)
Copied to clipboard
Sharmila Reddy Nangi, Atharv Tyagi, Jay Mundra, Sagnik Mukherjee, Raj Snehal, Niyati Chhaya, Aparna Garimella
| Challenge: | Recent efforts to develop deep learning models for text generation tasks are challenging for non-experts. |
| Approach: | They propose methods to automatically create deep learning models for extractive and abstractive summarization tasks using large language models. |
| Outcome: | The proposed methods achieve near state-of-the-art performance on a range of datasets. |
A Survey of Deep Learning for Mathematical Reasoning (2023.acl-long)
Copied to clipboard
| Challenge: | a survey of deep learning for mathematical reasoning examines the field . a comprehensive reading list is provided to assist readers interested in the field. |
| Approach: | They present a survey of deep learning for mathematical reasoning over the past decade . they outline directions for future research and highlight potential for further exploration . |
| Outcome: | The proposed framework is based on the results of a decade-long survey of deep learning for mathematical reasoning. |
Efficient Active Learning with Adapters (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies show that distilled versions of pretrained models are not always available. |
| Approach: | They propose to use distilled versions of successor models as acquisition models to reduce the training cost of the model. |
| Outcome: | The proposed approach reduces the training cost of the model and does not cause the acquisition-successor mismatch (ASM) problem. |
A Comparative Study on the Impact of Model Compression Techniques on Fairness in Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | Existing literature demonstrates that compressing deep learning models could affect their fairness. |
| Approach: | They evaluate pruned, distilled, and quantized language models to assess their fairness . they also examine the impact of using multilingual models and evaluation measures . |
| Outcome: | The proposed methods can reduce the fairness of language models by reducing their complexity and reducing the cost of training and deployment. |
Automate Strategy Finding with LLM in Quant Investment (2025.findings-emnlp)
Copied to clipboard
Zhizhuo Kou, Holam Yu, Junyu Luo, Jingshu Peng, Xujia Li, Chengzhong Liu, Juntao Dai, Lei Chen, Sirui Han, Yike Guo
| Challenge: | Experimental results demonstrate robust performance of the strategy in Chinese & US market regimes compared to established benchmarks. |
| Approach: | They propose a framework leveraging Large Language Models within a risk-aware multi-agent system for automate strategy finding in quantitative finance. |
| Outcome: | The proposed framework outperforms all benchmarks in Chinese & US market regimes with 53.17% cumulative return on SSE50. |
CLEAR: Character Unlearning in Textual and Visual Modalities (2025.findings-acl)
Copied to clipboard
Alexey Dontsov, Dmitrii Korzh, Alexey Zhavoronkin, Boris Mikheev, Denis Bobkov, Aibek Alanov, Oleg Rogov, Ivan Oseledets, Elena Tutubalina
| Challenge: | Existing methods for removing private or hazardous data from deep learning models are focused on single-modality models. |
| Approach: | They propose CLEAR, the first open-source benchmark specifically for MMU. CLEAR contains 200 fictitious individuals and 3,700 images linked with corresponding question-answer pairs. |
| Outcome: | The proposed benchmarks show that unlearning both modalities outperform single-modality approaches. |
New Datasets for Automatic Detection of Textual Entailment and of Contradictions between Sentences in French (2024.lrec-main)
Copied to clipboard
| Challenge: | DACCORD is a dataset for automatic detection of contradictions between sentences . it is the first dataset exclusively dedicated to this task . |
| Approach: | They introduce DACCORD, a dataset in French for automatic detection of contradictions between sentences. |
| Outcome: | The proposed datasets are more challenging than existing datasets for the mainstream task in French. |
VerifyMatch: A Semi-Supervised Learning Paradigm for Natural Language Inference with Confidence-Aware MixUp (2024.emnlp-main)
Copied to clipboard
| Challenge: | Natural language inference (NLI) is a key task for evaluating a model's ability to perform natural language understanding and reasoning. |
| Approach: | They propose to construct pseudo-generated samples using class-specific fine-tuned large language models (LLMs) . they retain all pseudo-labeled samples, but use MixUp to ensure unlabele . |
| Outcome: | The proposed approach achieves competitive accuracy compared to strong baselines for NLI datasets in low-resource settings. |
Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve? (2024.emnlp-main)
Copied to clipboard
| Challenge: | In the last decade, the generalization and adaptation abilities of deep learning models were evaluated on fixed training and test distributions. |
| Approach: | They propose to train large language models on unlabeled text corpora and train them online. |
| Outcome: | The proposed model training on a text domain could degrade its perplexity on the test portion of the same domain. |
TransLLM: A Unified Multi-Task Large Language Model for Urban Transportation via Learnable Prompting (2026.acl-long)
Copied to clipboard
| Challenge: | Existing models lack generalization capabilities and lack structured spatiotemporal data. |
| Approach: | They propose a unified multi-task framework that synergizes spatiotemporal encoding with LLM reasoning through learnable prompt composition. |
| Outcome: | The proposed framework outperforms baseline models on seven datasets and three tasks on supervised and zero-shot settings with excellent generalization and robustness. |
Mitigating Spurious Correlations in Text Classification Using Latent Space Geometry (2026.acl-long)
Copied to clipboard
| Challenge: | Existing models rely on predictive shortcuts that hold in training data but break under distribution shifts, leading to large performance drops for minority groups. |
| Approach: | They propose a framework that transforms abstract biases into interpretable geometric anchors without auxiliary classifiers by manipulating latent space geometry. |
| Outcome: | The proposed framework outperforms state-of-the-art baselines and improves worst-group accuracy by over 20% on the CivilComments dataset. |
So Hateful! Building a Multi-Label Hate Speech Annotated Arabic Dataset (2024.lrec-main)
Copied to clipboard
| Challenge: | Social media enables widespread propagation of hate speech targeting groups based on ethnicity, religion, or other characteristics. |
| Approach: | They analyze 70,000 Arabic tweets to identify hate speech patterns and train models . 15% of tweets contain offensive language while 6% have hate speech . authors hope to prevent spread of hateful content on social media platforms . |
| Outcome: | The analysis of 70,000 Arabic tweets shows that 15% of tweets contain offensive language while 6% have hate speech . 10% of tweet provide verifiable factual claims, and 7% are deemed important . |
AutoCT: Automating Interpretable Clinical Trial Prediction with LLM Agents (2025.emnlp-main)
Copied to clipboard
| Challenge: | Clinical trials are expensive and time-consuming, and accurate trial prediction is key to advancing medical treatments. |
| Approach: | They propose a framework that combines reasoning capabilities of large language models with the explainability of classical machine learning to generate, evaluate, and refine tabular features without human input. |
| Outcome: | The proposed framework performs better than SOTA methods on clinical trial prediction tasks within a limited number of iterations. |
SUE: Sparsity-based Uncertainty Estimation via Sparse Dictionary Learning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to estimate uncertainty use predictive confidence, structural characteristics of representation space, or stochastic variation in model outputs. |
| Approach: | They propose a new uncertainty estimation framework based on sparse dictionary learning by identifying dictionary atoms associated with misclassified samples. |
| Outcome: | The proposed framework outperforms or matches existing methods on several NLU benchmarks and sentiment analysis benchmarks. |
A Counterfactual Explanation Framework for Retrieval Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing literature on explainability of information retrieval has focused on illustrating the concept of relevance concerning a retrieval model. |
| Approach: | They propose to add terms to a document to improve its ranking to answer the question of which words played a role in not being favored by a retrieval model. |
| Outcome: | The proposed framework predicts counterfactuals for statistical and deep-learning models. |