NEURAL NETWORK MODELS

AutoNLU: An On-demand Cloud-based Natural Language Understanding System for Enterprises (2020.aacl-demo)

Challenge:	Large pre-trained language models have hundreds of millions of parameters and take several gigabytes of memory to train and inference.
Approach:	They propose an open-source knowledge distillation toolkit designed for natural language processing that provides a set of predefined distillation methods and can be extended with custom code.
Outcome:	The proposed method is comparable with or even higher than the public distilled BERT models with similar numbers of parameters.

Copied to clipboard

Nham Le, Tuan Lai, Trung Bui, Doo Soon Kim

Challenge:	AutoNLU is an on-demand cloud-based system that enables users to create and edit datasets and train and test different state-of-the-art NLU models.
Approach:	They introduce an on-demand cloud-based system that provides an easy-to-use interface . they build powerful keyphrase extraction models that achieve state-of-the-art results .
Outcome:	The proposed model achieves state-of-the-art on two public benchmarks and is easy to use and use.

Variational Inference and Deep Generative Models (P18-5)

Copied to clipboard

Wilker Aziz, Philip Schulz

The Amazing World of Neural Language Generation (2020.emnlp-tutorials)

Challenge:	Unsupervised and semi-supervised learning has been addressed scarcely in NLP . this tutorial provides an introduction to variational inference followed by an example-driven discussion of how to use variational methods for training DGMs.
Approach:	This tutorial provides an introduction to variational inference followed by an example-driven discussion of how to use variational methods for training DGMs.
Outcome:	This tutorial provides an introduction to variational inference followed by an example-driven discussion of how to use variational methods for training DGMs.

Copied to clipboard

Yangfeng Ji, Antoine Bosselut, Thomas Wolf, Asli Celikyilmaz

Generating Text through Adversarial Training Using Skip-Thought Vectors (N19-3)

Challenge:	Recent years have seen a paradigm shift in neural text generation due to advances in deep contextual language modeling and transfer learning.
Approach:	They will discuss how and why NLG models succeed/fail at generating coherent text.
Outcome:	This paper will discuss how and why these models succeed/fail at generating coherent text, and provide insights on several applications.

Copied to clipboard

Afroz Ahamad

Robustness in NLP

Challenge:	Existing approaches to use word embeddings for text generation have been limited.
Approach:	They propose to use GANs with word embeddings to reproduce writing style in text . they use a sentence embeddable vector to model people's way of expression .
Outcome:	The proposed model outperforms baseline text generation networks across several metrics including BLEU-n, METEOR and ROUGE.

Does Syntax Need to Grow on Trees? Sources of Hierarchical Inductive Bias in Sequence-to-Sequence Networks (2020.tacl-1)

Copied to clipboard

R. Thomas McCoy, Robert Frank, Tal Linzen

Syntactic Text Processing

Challenge:	Inductive biases can arise from any aspect of the model architecture, study finds . we investigate which architectural factors affect how models generalize .
Approach:	They investigate which architectural factors affect generalization behavior of neural network models . they use English question formation and English tense reinflection as test cases .
Outcome:	The findings suggest that human-like generalization requires architectural syntactic structure.

Affection Driven Neural Networks for Sentiment Analysis (2020.lrec-1)

Copied to clipboard

Rong Xiang, Yunfei Long, Mingyu Wan, Jinghang Gu, Qin Lu, Chu-Ren Huang

Benchmarks and models for entity-oriented polarity detection (N18-3)

Challenge:	Existing deep neural network models lack mechanisms to highlight important sentiment terms.
Approach:	They propose a method to incorporate affective knowledge into deep neural network models by mapping affective influence vectors to an affective impact value and integrating them into long-term memory models to highlight affective terms.
Outcome:	The proposed approach improves on three large datasets by 1.0% to 1.5% on the benchmark datasets.

Copied to clipboard

Lidia Pivovarova, Arto Klami, Roman Yangarber

Information Retrieval

Challenge:	a dataset of 17,000 manually labeled documents is large for determining entity-oriented polarity in business news.
Approach:	They propose a convolutional neural network-based approach to classify entity-oriented polarity in business news.
Outcome:	The proposed model is based on convolutional neural networks and is small on the scale of existing models.

How does Attention Affect the Model? (2021.findings-acl)

Copied to clipboard

Cheng Zhang, Qiuchi Li, Lingyu Hua, Dawei Song

Explainability & Interpretability in NLP

Challenge:	Existing studies on the effectiveness of attention in NLP do not consider changes in semantic capability of different components.
Approach:	They propose a framework that exploits a convex hull representation of sequence semantics in an n-dimensional Semantic Euclidean Space and defines indicators to capture the impact of attention on sequence semantic.
Outcome:	The proposed framework exploits a convex hull representation of sequence semantics in an n-dimensional Semantic Euclidean Space and defines indicators to capture the impact of attention on sequence semantic.

Neural Unsupervised Parsing Beyond English (D19-61)

Copied to clipboard

Katharina Kann, Anhad Mohananey, Samuel R. Bowman, Kyunghyun Cho

Robustness Evaluation of Text Classification Models Using Mathematical Optimization and Its Application to Adversarial Training (2022.findings-aacl)

Challenge:	Unsupervised parsing is a task that can be learned without substantial prior knowledge.
Approach:	They train an unsupervised model for Arabic, Chinese, English, and German to learn syntactic structure from unlabeled text.
Outcome:	The PRPN architecture outperforms trivial baselines and acquires at least some parsing ability for all languages.

Copied to clipboard

Hikaru Tomonari, Masaaki Nishino, Akihiro Yamamoto

Robustness in NLP

Challenge:	Neural networks are vulnerable to adversarial examples due to slightly perturbed input data.
Approach:	They propose a method that evaluates the robustness of text classification models by an optimization problem that identifies a minimum synonym swap that changes the classification result.
Outcome:	The proposed method achieves high scores in human evaluations of grammatical correctness and semantic similarity for an IMDb dataset and implements adversarial training with the IMD and SST2 datasets.

Introducing Two Vietnamese Datasets for Evaluating Semantic Models of (Dis-)Similarity and Relatedness (N18-2)

Copied to clipboard

Kim Anh Nguyen, Sabine Schulte im Walde, Ngoc Thang Vu

Semantic Similarity

Challenge:	Existing datasets for low-resource language Vietnamese assess semantic similarity . a dataset for word pairs with similarity levels is needed to evaluate these models .
Approach:	They present two new datasets for the low-resource language Vietnamese to assess models of semantic similarity.
Outcome:	The two datasets are comparable to the English datasets.

End-to-end Argument Mining with Cross-corpora Multi-task Learning (2022.tacl-1)

Copied to clipboard

Gaku Morio, Hiroaki Ozaki, Terufumi Morishita, Kohsuke Yanai

Speaker-change Aware CRF for Dialogue Act Classification (2020.coling-main)

Challenge:	Argument(ation) mining is a task of identifying argument structure from text . lack of training data makes it difficult to train models based on limited data sets.
Approach:	They propose an end-to-end cross-corpus argument mining method that uses auxiliary argument mining corpora to train models.
Outcome:	The proposed method outperforms models trained on a single corpus on arguments on arguments in argument mining tasks.

Copied to clipboard

Guokan Shang, Antoine Tixier, Michalis Vazirgiannis, Jean-Pierre Lorré

Information Retrieval

Challenge:	Recent work in Dialogue Act (DA) classification approaches the task as a sequence labeling problem, using neural network models coupled with a Conditional Random Field (CRF) as the last layer.
Approach:	They propose to modify the CRF layer to take speaker-change into account and learn meaningful transition patterns conditioned on speaker-changing DA labels.
Outcome:	The proposed model outperforms the original model with wide margins for some DA labels.

Inducing Grammar from Long Short-Term Memory Networks by Shapley Decomposition (2020.acl-srw)

Copied to clipboard

Yuhui Zhang, Allen Nie

Syntactic Text Processing

Challenge:	a recent study shows that modern neural networks understand sentences implicitly by inducing recursive structures.
Approach:	They propose to explicitly induce grammar by tracing the computational process of a long short-term memory network.
Outcome:	The proposed model can explicitly induce grammar without external knowledge . tracing the computational process of a long short-term memory network is shown to be effective .

Temporal Event Knowledge Acquisition via Identifying Narratives (P18-1)

Copied to clipboard

Wenlin Yao, Ruihong Huang

Challenge:	Existing knowledge of narrative examples is lacking and difficult to obtain.
Approach:	They propose a weakly supervised approach for acquiring rich temporal event knowledge across sentences in narrative stories.
Outcome:	The proposed approach outperforms neural network models on the narrative cloze task.

Deep Reinforcement Learning for Chinese Zero Pronoun Resolution (P18-1)

Copied to clipboard

Qingyu Yin, Yu Zhang, Wei-Nan Zhang, Ting Liu, William Yang Wang

Querying Word Embeddings for Similarity and Relatedness (N18-1)

Challenge:	Recent models for zero pronoun resolution in Chinese are short-sighted and do not capture semantic information for zeros and candidate antecedents.
Approach:	They propose to integrate a deep reinforcement learning approach to Chinese zero pronoun resolution.
Outcome:	The proposed approach outperforms the state-of-the-art methods in three experimental settings.

Copied to clipboard

Fatemeh Torabi Asr, Robert Zinkov, Michael Jones

Representation Learning

Challenge:	Word2Vec embeddings have become popular representations of word meaning . similarity between two words is often assumed to be a direction-less measure, whereas relatedness is inherently directional.
Approach:	They propose to use word embeddings to predict asymmetric association between words from a dataset of production norms to generate thematically related words.
Outcome:	The proposed model predicts asymmetric association between words from a recently published dataset of production norms.

End-to-end Deep Reinforcement Learning Based Coreference Resolution (P19-1)

Copied to clipboard

Hongliang Fei, Xu Li, Dingcheng Li, Ping Li

Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing (P18-1)

Challenge:	Recent neural network models for coreference resolution are usually trained with heuristic loss functions that are computed over a sequence of local decisions.
Approach:	They propose an end-to-end reinforcement learning based coreference resolution model to directly optimize coreference evaluation metrics.
Outcome:	The proposed model achieves new state-of-the-art performance on the English OntoNotes v5.0 benchmark.

Copied to clipboard

Bo Chen, Le Sun, Xianpei Han

Constituency Lattice Encoding for Aspect Term Extraction (2020.coling-main)

Challenge:	Existing methods for semantic parsing are difficult to design and learn, especially in wideopen domains.
Approach:	They propose a neural semantic parsing approach which models semantic par- sing as an end-to-end semantic graph generation process.
Outcome:	The proposed model achieves state-of-the-art performance on Overnight dataset and gets competitive performance on Geo and Atis datasets.

Copied to clipboard

Yunyi Yang, Kun Li, Xiaojun Quan, Weizhou Shen, Qinliang Su

Unsupervised Deep Structured Semantic Models for Commonsense Reasoning (N19-1)

Challenge:	a challenge for aspect term extraction is to extract phrase-level aspect terms . a constituency lattice structure is constructed using the span annotations of constituents of a sentence .
Approach:	They propose to incorporate the span annotations of constituents of a sentence to leverage syntactic information in neural network models.
Outcome:	The proposed model outperforms existing models on two benchmark datasets.

Copied to clipboard

Shuohang Wang, Sheng Zhang, Yelong Shen, Xiaodong Liu, Jingjing Liu, Jianfeng Gao, Jing Jiang

Reasoning

Challenge:	Existing methods for commonsense reasoning rely on human-crafted features and knowledge bases, but unsupervised learning is not feasible due to the lack of labeled training data or comprehensive knowledge bases.
Approach:	They propose two unsupervised models based on the Deep Structured Semantic Models framework to tackle two commonsense reasoning tasks: Winograd Schema Challenge (WSC) and Pronoun Disambiguation (PDP).
Outcome:	The proposed models capture contextual information in the sentence and co-reference information between pronouns and nouns, and achieve significant improvement over previous state-of-the-art approaches.

Predicting Foreign Language Usage from English-Only Social Media Posts (N18-2)

Copied to clipboard

Svitlana Volkova, Stephen Ranshous, Lawrence Phillips

Multilinguality

Challenge:	Social media is known for its multi-cultural and multilingual interactions, a natural product of which is code-mixing.
Approach:	They analyze 6 million tweets produced by 27 thousand multilingual users speaking 12 other languages besides English to build predictive models to infer non-English languages users speak exclusively from their tweets.
Outcome:	The proposed models are based on a corpus of 6 million tweets produced by 27 thousand multilingual users speaking 12 other languages besides English . they show that content, style and syntax are the most predictive of non-English languages that users speak on Twitter.

Event Detection with Neural Networks: A Rigorous Empirical Evaluation (D18-1)

Copied to clipboard

Walker Orr, Prasad Tadepalli, Xiaoli Fern

MuCPAD: A Multi-Domain Chinese Predicate-Argument Dataset (2022.naacl-main)

Challenge:	Neural network models have been the most successful for event detection, but they ignore syntactic relationships in the text.
Approach:	They propose a GRU-based model that combines syntactic information along with temporal structure through an attention mechanism.
Outcome:	The proposed model is competitive with existing models on a ACE2005 dataset.

Copied to clipboard

Yahui Liu, Haoping Yang, Chen Gong, Qingrong Xia, Zhenghua Li, Min Zhang

Challenge:	Recent studies show that shallow semantic role labeling (SRL) performance drops under out-of-domain setting.
Approach:	They propose to annotate a multi-domain Chinese predicate-argument dataset using a frame-free annotation methodology and strict double annotation for improving data quality.
Outcome:	The proposed dataset is compared with a dataset from six different domains.

Enhancing Long-range Dependency with State Space Model and Kolmogorov-Arnold Networks for Aspect-based Sentiment Analysis (2025.coling-main)

Copied to clipboard

Adamu Lawan, Juhua Pu, Haruna Yunusa, Aliyu Umar, Muhammad Lawan

A Neural Approach to Pun Generation (P18-1)

Challenge:	Aspect-based Sentiment Analysis (ABSA) evaluates sentiments toward specific aspects of entities within the text.
Approach:	They propose a method to enhance long-range dependencies between aspect and opinion words in ABSA by combining attention mechanisms with a syntax-based Graph Convolutional Network and a Mamba-Transformer module.
Outcome:	The proposed model outperforms state-of-the-art models on three benchmark datasets.

Copied to clipboard

Zhiwei Yu, Jiwei Tan, Xiaojun Wan

A Systematic Assessment of Syntactic Generalization in Neural Language Models (2020.acl-main)

Challenge:	generating puns with artificial intelligence techniques requires manual training and templates.
Approach:	They propose neural network models for homographic pun generation that can generate puns without requiring any pun data for training.
Outcome:	The proposed models generate homographic puns of good readability and quality without training.

Copied to clipboard

Jennifer Hu, Jon Gauthier, Peng Qian, Ethan Wilcox, Roger Levy

Age Recommendation for Texts (2020.lrec-1)

Challenge:	Existing work on syntactic knowledge models has not provided a clear picture of the properties required to produce proper syntaktic generalizations.
Approach:	They propose to evaluate syntactic knowledge of language models by varying model architectures . they find substantial differences in syntaktic generalization performance by model architecture .
Outcome:	The proposed model architectures outperform other architectures on a set of 34 English-language syntactic test suites.

Copied to clipboard

Alexis Blandin, Gwénolé Lecorvé, Delphine Battistelli, Aline Étienne

Challenge:	adequacy of a text’s characteristics with the person’s capacities and knowledge is critical in the case of . a child since her/his cognitive and linguistic skills are still under development.
Approach:	They propose a natural language processing task which consists in predicting the age from which a text can be understood by someone.
Outcome:	The proposed model outperforms psycholinguist models on a French text dataset and shows that the results are more accurate than psycholingual models.

Sequential Attention with Keyword Mask Model for Community-based Question Answering (N19-1)

Copied to clipboard

Jianxin Yang, Wenge Rong, Libin Shi, Zhang Xiong

Natural Language Interfaces

Challenge:	Existing methods to model answer selection(AS) are based on feature engineering and resource toolkits.
Approach:	They propose a model that captures features and information from question and answer text and repeats multiple times(hops) in a sequential fashion.
Outcome:	The proposed model performs on answer selection tasks and multi-level answer ranking tasks.

Learning Syntactic Dense Embedding with Correlation Graph for Automatic Readability Assessment (2021.acl-long)

Copied to clipboard

Xinying Qiu, Yuan Chen, Hanwu Chen, Jian-Yun Nie, Yuming Shen, Dawei Lu

Analogy Models for Neural Word Inflection (2020.coling-main)

Challenge:	Existing deep learning models for automatic readability assessment discard linguistic features traditionally used for the task.
Approach:	They propose to incorporate linguistic features into machine learning models by learning syntactic dense embeddings based on linguistic feature extraction.
Outcome:	Experiments with six data sets of two proficiency levels show that the proposed model can perform better than existing models.

Copied to clipboard

Ling Liu, Mans Hulden

Reasoning

Challenge:	Neural network models are usually very data-hungry and performance of such models can suffer when labeled data is not available.
Approach:	They propose to provide models with additional analogy sources to strengthen analogy-formation . they propose to combine the analogy motivated approach with data hallucination or augmentation .
Outcome:	The proposed methods improve on state-of-the-art results on 46 languages, especially in low-resource settings.

Leveraging Grammar Induction for Language Understanding and Generation (2024.findings-emnlp)

Copied to clipboard

Jushi Kai, Shengyuan Hou, Yusheng Huang, Zhouhan Lin

A Visually-grounded First-person Dialogue Dataset with Verbal and Non-verbal Responses (2020.emnlp-main)

Challenge:	Existing grammar induction methods do not provide sufficient performance in downstream tasks.
Approach:	They propose an unsupervised grammar induction method for language understanding and generation using a grammar parser and a syntactic mask.
Outcome:	The proposed method performs better on from-scratch and pre-trained scenarios.

Copied to clipboard

Hisashi Kamezawa, Noriki Nishida, Nobuyuki Shimizu, Takashi Miyazaki, Hideki Nakayama

Claim veracity assessment for explainable fake news detection (2025.coling-main)

Challenge:	In visual-grounded dialogue systems, first-person visual information about where the other speakers are and what they are paying attention to is crucial to understand their intentions.
Approach:	They propose a visually-grounded first-person dialogue (VFD) dataset with verbal and non-verbal responses.
Outcome:	The proposed dataset provides verbal and non-verbal responses for first-person visual information and recent neural network models.

Copied to clipboard

Bassamtiano Renaufalgi Irnawan, Sheng Xu, Noriko Tomuro, Fumiyo Fukumoto, Yoshimi Suzuki

Query-focused Scenario Construction (D19-1)

Challenge:	Recent approaches to fake news detection focus on textual features without external facts, which may lead to a misrepresentation of the truth.
Approach:	They propose a new fake news detection method that predicts the truth or false-hood of a claim based on relevant factual evidence or LLM’s inference mechanisms.
Outcome:	The proposed method produces the final synthesized prediction, along with well-founded facts or reasoning.

Copied to clipboard

Su Wang, Greg Durrett, Katrin Erk

Interpretable Neural Predictions with Differentiable Binary Variables (P19-1)

Challenge:	Stronger neural network models and harder synthetic training settings are important to achieve high performance.
Approach:	They propose a query-based system that extracts compatible sets of events from news data . stronger neural network models and harder synthetic training settings are important to achieve high performance .
Outcome:	The proposed system outperforms baselines on a human-curated dataset of scenarios about real-world news topics.

Copied to clipboard

Jasmijn Bastings, Wilker Aziz, Ivan Titov

Explainability & Interpretability in NLP

Challenge:	Neural networks are bringing incredible performance gains on text classification tasks, but they also require interpretability.
Approach:	They propose a latent model that selects a rationale and a classifier that learns from the words in the rationale alone.
Outcome:	The proposed model can predict expected value of penalties without REINFORCE and can be directly optimised towards a pre-specified text selection rate.

Disentangled Sequence to Sequence Learning for Compositional Generalization (2022.acl-long)

Copied to clipboard

Hao Zheng, Mirella Lapata

A Regularization Approach for Incorporating Event Knowledge and Coreference Relations into Neural Discourse Parsing (D19-1)

Challenge:	Existing models struggle to generalize to unseen compositions of seen components . a new approach allows for disentangled representations and better generalization .
Approach:	They propose an extension to sequence-to-sequence models which encourage disentanglement by re-encoding source input.
Outcome:	The proposed extension delivers better generalization and more disentangled representations . human expressions can be understood by combining known atomic components .

Copied to clipboard

Zeyu Dai, Ruihong Huang

Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks (2021.naacl-main)

Challenge:	Existing approaches to discourse parsing use commonsense knowledge and linguistic constraints to integrate them into neural network models.
Approach:	They propose a knowledge regularization approach that integrates linguistic constraints with contexts for deriving word representations.
Outcome:	The proposed approach outperforms previous systems on the benchmark dataset PDTB for discourse parsing.

Copied to clipboard

Hanjie Chen, Song Feng, Jatin Ganhotra, Hui Wan, Chulaka Gunasekara, Sachindra Joshi, Yangfeng Ji

Handling Extreme Class Imbalance in Technical Logbook Datasets (2021.acl-long)

Challenge:	Existing methods to explain neural network models are computationally inefficient for text inputs.
Approach:	They propose a method to implicitly detect word correlations by grouping correlated words from input text pairs together and measuring their contribution to corresponding NLP tasks.
Outcome:	The proposed method is evaluated with two different model architectures across four datasets.

Copied to clipboard

Farhad Akhbardeh, Cecilia Ovesdotter Alm, Marcos Zampieri, Travis Desell

Grapheme-to-Phoneme Conversion for Thai using Neural Regression Models (2022.naacl-main)

Challenge:	Technical logbooks are a challenging and under-explored text type in automated event identification.
Approach:	They propose a feedback strategy that resamples the training data based on its error in the prediction process.
Outcome:	The proposed approach provides the best results for four different neural network models trained across a suite of technical logbook datasets from distinct technical domains.

Copied to clipboard

Tomohiro Yamasaki

Predicting Helpful Posts in Open-Ended Discussion Forums: A Neural Architecture (N19-1)

Challenge:	Grapheme-to-phoneme conversion is a task of converting grapheme sequences into phoneme sequence.
Approach:	They propose a Thai grapheme-to-phoneme conversion method that uses neural networks to predict the similarity between a candidate and the correct pronunciation.
Outcome:	The proposed method can be applied to other languages than Thai . it is comparable to encoder-decoder models in accuracy and accuracy, it shows .

Copied to clipboard

Kishaloy Halder, Min-Yen Kan, Kazunari Sugiyama

Challenge:	Unlike Community Question Answering, where questions are mostly factoid based, forum threads are often open-ended and contain repetitive or irrelevant posts.
Approach:	They propose a recurrent neural network-based architecture to model the relevance of a post regarding the original post starting the thread and the novelty it brings to the discussion.
Outcome:	The proposed model outperforms the state-of-the-art models for text classification on different types of online forum datasets.

Investigating Dynamic Routing in Tree-Structured LSTM for Sentiment Analysis (D19-1)

Copied to clipboard

Jin Wang, Liang-Chih Yu, K. Robert Lai, Xuejie Zhang

Energy and Policy Considerations for Deep Learning in NLP (P19-1)

Challenge:	Existing deep neural network models such as LSTM and tree-LSTM have a bias problem where the words in the tail of a sentence are more heavily emphasized than those in the header.
Approach:	They propose a capsule tree-LSTM model that uses dynamic routing to build sentence representations by assigning different weights to nodes according to their contributions to prediction.
Outcome:	The proposed model improves on the Stanford Sentiment Treebank and EmoBank datasets.

Copied to clipboard

Emma Strubell, Ananya Ganesh, Andrew McCallum

PixT3: Pixel-based Table-To-Text Generation (2024.acl-long)

Challenge:	Recent advances in hardware and methodology for training neural networks have enabled significant accuracy improvements across many NLP tasks.
Approach:	They quantify the approximate financial and environmental costs of training neural network models . they propose actionable recommendations to reduce costs and improve equity in NLP research .
Outcome:	The proposed recommendations address the cost and environmental costs of training neural networks for NLP.

Copied to clipboard

Iñigo Alonso, Eneko Agirre, Mirella Lapata

Structured Data in NLP

Challenge:	Table-to-text generation is a visual recognition task that uses textual descriptions from structured inputs.
Approach:	They propose to rethink data-to-text generation as a visual recognition task by removing the need for rendering the input in a string format.
Outcome:	The proposed model overcomes the challenges of linearization and input size limitations and is applicable to open-ended and controlled generation settings.

Block-wise Word Embedding Compression Revisited: Better Weighting and Structuring (2021.findings-emnlp)

Copied to clipboard

Jong-Ryul Lee, Yong-Ju Lee, Yong-Hyuk Moon

Lexicon Learning for Few Shot Sequence Modeling (2021.acl-long)

Challenge:	Existing methods for word embedding compression are limited . word embeds have a considerable size and need to be compressed to deploy on edge devices .
Approach:	They propose a block-wise low-rank approximation method for word embedding called GroupReduce . they propose 'frequency-inverse document frequency method' and a differentiable method for weighting .
Outcome:	The proposed algorithm more effectively finds word weights than competitors in most cases.

Copied to clipboard

Ekin Akyurek, Jacob Andreas

MRF-Chat: Improving Dialogue with Markov Random Fields (2021.emnlp-main)

Challenge:	Past work has shown that many failures of systematic generalization arise from neural models’ inability to disentangle lexical phenomena from syntactic ones.
Approach:	They propose a lexical translation mechanism that generalizes existing copy mechanisms to incorporate learned, decontextualized, token-level translation rules.
Outcome:	The proposed model improves generalization on a diverse set of sequence modeling tasks drawn from cognitive science, formal semantics, and machine translation.

Copied to clipboard

Ishaan Grover, Matthew Huggins, Cynthia Breazeal, Hae Won Park

A Large-Scale Corpus of E-mail Conversations with Standard and Two-Level Dialogue Act Annotations (2020.coling-main)

Challenge:	Existing approaches to deep learning for open-domain dialogue include training end-to-end models to learn various conversational features like emotional content of response, symbolic transitions of dialogue contexts and persona of the agent and the user, among others.
Approach:	They propose a probabilistic approach using Markov Random Fields to augment existing deep-learning methods for improved next utterance prediction.
Outcome:	The proposed approach significantly improves the performance of existing state-of-the-art retrieval models for open-domain conversational agents.

Copied to clipboard

Motoki Taniguchi, Yoshihiro Ueda, Tomoki Taniguchi, Tomoko Ohkuma

Multi-Vector Attention Models for Deep Re-ranking (2021.emnlp-main)

Challenge:	e-mail conversations have domain-agnostic and two-level dialogue act annotations . et al. (2017): a better understanding of asynchronous conversations.
Approach:	They present a large-scale corpus of e-mail conversations with domain-agnostic and two-level dialogue act annotations . they use ISO standard 24617-2 as the annotation scheme to annotate over 6,000 messages and 35,000 sentences .
Outcome:	The proposed model outperforms other neural networks but falls short of human performance.

Copied to clipboard

Giulio Zhou, Jacob Devlin

Learning Adverbs with Spectral Mixture Kernels (2024.findings-acl)

Challenge:	Document retrieval systems often use two styles of neural network models . dual encoder models are used for retrieval and deep re-ranking, while cross-attention models are typically used for shallow reranking.
Approach:	They propose a dual encoder and cross-attention neural network architectures that combine query and document representations to optimize retrieval accuracy.
Outcome:	The proposed architecture trades off retrieval accuracy with joint computation and offline document storage cost.

Copied to clipboard

Tomoe Taniguchi, Daichi Mochihashi, Ichiro Kobayashi

Cross-Lingual Unsupervised Sentiment Classification with Multi-View Transfer Learning (2020.acl-main)

Challenge:	In order for robots to collaborate with humans, it is important to share and understand their experiences through language.
Approach:	They propose a hierarchical Dirichlet Process-Spectral Mixture Latent Dirichlets Allocation model which learns the relationship between human motions and adverbs by capturing frequency kernels that represent motion characteristics and shared topics of a given aadverts.
Outcome:	The proposed model outperforms representative neural network models in terms of perplexity score and predicts more appropriate adverbs.

Copied to clipboard

Hongliang Fei, Ping Li

Information Retrieval

Challenge:	Recent neural network models have achieved impressive performance on sentiment classification in English and other languages.
Approach:	They propose an unsupervised sentiment classification model that leverages an uncontrolled machine translation system and a language discriminator to learn a shared representation.
Outcome:	The proposed model outperforms other models on five language pairs.

Grammar Induction with Neural Language Models: An Unusual Replication (D18-1)

Copied to clipboard

Phu Mon Htut, Kyunghyun Cho, Samuel Bowman

A Knowledge Regularized Hierarchical Approach for Emotion Cause Analysis (D19-1)

Challenge:	Recent work on latent tree learning attempts to develop models with parse-valued latent variables and train them on non-parsing tasks.
Approach:	They propose a model with parse-valued latent variables and a strong latent tree learning result on constituency parsing.
Outcome:	The proposed model outperforms all baselines and performs competitively with symbolic grammar induction systems.

Copied to clipboard

Chuang Fan, Hongyu Yan, Jiachen Du, Lin Gui, Lidong Bing, Min Yang, Ruifeng Xu, Ruibin Mao

Observing Dialogue in Therapy: Categorizing and Forecasting Behavioral Codes (P19-1)

Challenge:	Emotion cause analysis aims to identify the reasons behind emotions . previous models focus on learning architecture with local textual information .
Approach:	They propose a method to extract emotion cause with hierarchical neural model and knowledge-based regularizations by sentiment lexicon and common knowledge.
Outcome:	The proposed method outperforms baselines on two public datasets in different languages and outperformed competitive baselines by 2.08%.

Copied to clipboard

Jie Cao, Michael Tanana, Zac Imel, Eric Poitras, David Atkins, Vivek Srikumar

Continual Lifelong Learning in Natural Language Processing: A Survey (2020.coling-main)

Challenge:	a new study examines the role of dialogue observers in psychotherapy . the model is based on motivational interviewing, which is effective for treating addictions .
Approach:	They propose to model MI behavioral codes for therapists by an observer . they propose to use the observer to forecast therapist and client MI behavioral code .
Outcome:	The proposed model outperforms baseline models for both tasks and reveals tradeoffs in performance.

Copied to clipboard

Magdalena Biesialska, Katarzyna Biesialska, Marta R. Costa-jussà

Challenge:	Existing approaches to continual learning (CL) are costly and time-consuming.
Approach:	They propose to examine the problem of continual learning in NLP through the lens of various NLP tasks and provide a critical review of existing methods.
Outcome:	The proposed methods are critical to the development of CL models and provide a critical review of existing methods and datasets.

Neuro-Symbolic Sentiment Analysis with Dynamic Word Sense Disambiguation (2023.findings-emnlp)

Copied to clipboard

Xulang Zhang, Rui Mao, Kai He, Erik Cambria

Explainability & Interpretability in NLP

Challenge:	Traditional neural network models represent word senses as vectors that are uninterpretable for humans.
Approach:	They propose a framework that incorporates word Sense Disambiguation (WSD) by identifying and paraphrasing ambiguous words to improve sentiment predictions.
Outcome:	The proposed framework improves sentiment analysis accuracy and interpretability on a downstream task without ground-truth word sense labels.

Using Human Attention to Extract Keyphrase from Microblog Post (P19-1)

Copied to clipboard

Yingyi Zhang, Chengzhi Zhang

Sentence Centrality Revisited for Unsupervised Summarization (P19-1)

Challenge:	Existing studies on keyphrase extraction neglect human reading behavior during keyphrase annotating.
Approach:	They propose to integrate human attention into keyphrase extraction models by an attention mechanism and combine it with neural network models.
Outcome:	The proposed models improve on two Twitter datasets.

Copied to clipboard

Hao Zheng, Mirella Lapata

Numeracy-600K: Learning Numeracy for Detecting Exaggerated Information in Market Comments (P19-1)

Challenge:	Experimental results on three news summarization datasets representative of different languages and writing styles show that our approach outperforms strong baselines by a wide margin.
Approach:	They propose an unsupervised approach that uses a popular ranking algorithm to compute node centrality.
Outcome:	The proposed approach outperforms baselines on three news summarization datasets representative of different languages and writing styles.

Copied to clipboard

Chung-Chi Chen, Hen-Hsen Huang, Hiroya Takamura, Hsin-Hsi Chen

Challenge:	Numeracy is the ability to predict the magnitude of a numeral at some specific position in a text description.
Approach:	They propose to use a dataset to test whether neural network models can learn numeracy . numerability is the ability to predict the magnitude of a numeral at some specific position in a text description.
Outcome:	The proposed task can predict the magnitude of a numeral at a specific position in a text description.

Automatic Labeling of Problem-Solving Dialogues for Computational Microgenetic Learning Analytics (L18-1)

Copied to clipboard

Yuanliang Meng, Anna Rumshisky, Florence Sullivan

Soft Gazetteers for Low-Resource Named Entity Recognition (2020.acl-main)

Challenge:	This paper presents a recurrent neural network model to automate the analysis of students' computational thinking in problem-solving dialogue.
Approach:	They propose a recurrent neural network model to automate the analysis of students' computational thinking in problem-solving dialogue.
Outcome:	The proposed model outperforms the baseline model and outperformed the nave model by a large margin.

Copied to clipboard

Shruti Rijhwani, Shuyan Zhou, Graham Neubig, Jaime Carbonell

Named Entity Recognition

Challenge:	Existing named entity recognition models use gazetteers to improve performance, but they are limited in coverage and do not exist in low-resource languages.
Approach:	They propose a method that integrates Wikipedia information into named entity models by cross-lingual entity linking.
Outcome:	The proposed method improves on four low-resource languages with Wikipedia . it incorporates available information from english knowledge bases into neural models .

From Isolates to Families: Using Neural Networks for Automated Language Affiliation (2025.acl-long)

Copied to clipboard

Frederic Blum, Steffen Herbold, Johann-Mattis List

Multilinguality

Challenge:	linguistic affiliation of languages to a common language family is traditionally carried out manually . large-scale standardized collections of multilingual wordlists and grammatical language structures could improve this .
Approach:	They propose to use lexical and grammatical data to classify languages into families using neural network models.
Outcome:	The proposed models outperform models trained on lexical and grammatical data while combining both types of data yields even better performance.

Towards Understanding the Relationship between In-context Learning and Compositional Generalization (2024.lrec-main)

Copied to clipboard

Sungjun Han, Sebastian Padó