Papers by Eduard Hovy

EvEntS ReaLM: Event Reasoning of Entity States via Language Models (2022.emnlp-main)

Challenge:	Existing methods for event argument extraction are limited by the limited amount of annotations available.
Approach:	They propose to use SRL annotations for event argument extraction . they propose to specify natural language-like queries to tackle label mismatch problem .
Outcome:	The proposed model achieves impressive zero-shot results on English benchmarks . it also provides benefits in low-resource cases, where few annotations are available .

Copied to clipboard

Evangelia Spiliopoulou, Artidoro Pagnoni, Yonatan Bisk, Eduard Hovy

Low-Resource NLP

Challenge:	Existing approaches to model event implications fail to reason about the world, despite their knowledge of physical attributes.
Approach:	They propose to use a model prompting technique to prompt models of event implications by targeting their understanding of physical attributes.
Outcome:	The proposed model prompting technique is especially useful for unseen attributes or when only limited data is available.

Do Sentence Interactions Matter? Leveraging Sentence Level Representations for Fake News Classification (D19-53)

Copied to clipboard

Vaibhav Vaibhav, Raghuram Mandyam, Eduard Hovy

Ethical NLP

Challenge:	Existing methods to distinguish between trusted and fake news articles lack feature engineering . et al. (2009) define fake news as the one which deliberately exposes real-world individuals, organisations and events to ridicule.
Approach:	They propose a graph neural network-based model which captures sentence interactions within a document.
Outcome:	The proposed model beats baselines and achieves state-of-the-art accuracy on existing datasets.

From Credit Assignment to Entropy Regularization: Two New Algorithms for Neural Sequence Prediction (P18-1)

Copied to clipboard

Zihang Dai, Qizhe Xie, Eduard Hovy

Challenge:	equivalence between credit assignment problem and entropy regularized reinforcement learning is established . a wide range of successful sequence prediction algorithms have been developed .
Approach:	They propose to extend credit assignment in reward augmented maximum likelihood learning by credit assignment and entropy regularization.
Outcome:	The proposed algorithms outperform RAML and Actor-Critic on two benchmark datasets.

Learning to Generate Move-by-Move Commentary for Chess Games from Large-Scale Social Forum Data (P18-1)

Copied to clipboard

Harsh Jhamtani, Varun Gangal, Eduard Hovy, Graham Neubig, Taylor Berg-Kirkpatrick

Challenge:	Using a large-scale chess commentary dataset, we generate a set of comments for individual moves in a game.
Approach:	They propose a large-scale chess commentary dataset and a method to generate commentary for individual moves in a chessian game.
Outcome:	The proposed method is rated similar to ground truth commentary texts in terms of correctness and fluency.

Measuring Forecasting Skill from Text (2020.acl-main)

Copied to clipboard

Shi Zong, Alan Ritter, Eduard Hovy

Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis (2021.acl-long)

Challenge:	Prior studies have shown that some individuals can make accurate predictions with consistently better accuracy.
Approach:	They examine linguistic factors associated with people's predictions including uncertainty, readability, and emotion.
Outcome:	The proposed model can accurately predict forecasting skill using only language.

Copied to clipboard

Ruifan Li, Hao Chen, Fangxiang Feng, Zhanyu Ma, Xiaojie Wang, Eduard Hovy

NewsClaims: A New Benchmark for Claim Detection from News with Attribute Knowledge (2022.emnlp-main)

Challenge:	Existing methods to model relationships between aspects and opinion words are inefficient due to informal expressions and complexity of online reviews.
Approach:	They propose a dual graph convolutional networks model that considers complementarity of syntax structures and semantic correlations simultaneously.
Outcome:	The proposed model outperforms state-of-the-art methods on three public datasets and validates it.

Copied to clipboard

Revanth Gangi Reddy, Sai Chetan Chinthakindi, Zhenhailong Wang, Yi Fung, Kathryn Conger, Ahmed ELsayed, Martha Palmer, Preslav Nakov, Eduard Hovy, Kevin Small, Heng Ji

Linguistic Versus Latent Relations for Modeling Coherent Flow in Paragraphs (D19-1)

Challenge:	Current claims detection methods focus on sentence analysis, ignoring other attributes . a key element of identifying misinformation is detecting the claims and the arguments that have been presented.
Approach:	They propose a benchmark for attribute-aware claim detection in the news domain . they extend the problem to include extraction of additional attributes related to each claim .
Outcome:	The proposed system performs well on the test, but human performance is still poor.

Copied to clipboard

Dongyeop Kang, Eduard Hovy

(Male, Bachelor) and (Female, Ph.D) have different connotations: Parallelly Annotated Stylistic Language Dataset with Multiple Personas (D19-1)

Challenge:	a novel approach to paragraph planning involves a high-level control of different levels of relations between sentences . a proposed model with both forms of relations outperforms baselines in partially conditioned paragraph generation task .
Approach:	They propose two models that integrate human-created and latent relations into document-level language models . they focus on paragraph-level plan between sentences to produce coherent text .
Outcome:	The proposed models outperform baselines in partially conditioned paragraph generation task.

Copied to clipboard

Dongyeop Kang, Varun Gangal, Eduard Hovy

Challenge:	Despite recent attempts on computational modeling of the variation, the lack of parallel corpora of style language makes it difficult to systematically control the stylistic change and evaluate such models.
Approach:	They propose to use a parallel and annotated stylistic language dataset to test the effectiveness of style transfer models.
Outcome:	The proposed model outperforms the unsupervised models using nonparallel corpus.

A Sentiment Consolidation Framework for Meta-Review Generation (2024.acl-long)

Copied to clipboard

Miao Li, Jey Han Lau, Eduard Hovy

Low-Resource NLP

Challenge:	Recent advances in abstractive text summarization have created plausible summaries, but it is unclear if they truly possess the capability of information consolidation to generate summary.
Approach:	They propose to prompt large language models to generate meta-reviews and use evaluation metrics to assess the quality of generated meta- reviews.
Outcome:	The proposed framework proves that human meta-reviewers follow a framework of sentiment consolidation to write meta- reviews compared with prompting them with simple instructions.

Summarizing Multiple Documents with Conversational Structure for Meta-Review Generation (2023.findings-emnlp)

Copied to clipboard

Miao Li, Eduard Hovy, Jey Lau

Dialogue Systems & Conversational Agents

Challenge:	Existing models for abstractive text summarization do not provide explicit interdocument relationships among source documents.
Approach:	They propose a model that uses sparse attention based on the conversational structure and a multi-task training objective that predicts metadata features.
Outcome:	The proposed model outperforms baseline models in terms of evaluation metrics but struggle to handle conflicts in source documents.

Packing Analysis: Packing Is More Appropriate for Large Models or Datasets in Supervised Fine-tuning (2025.findings-acl)

Copied to clipboard

Shuhe Wang, Guoyin Wang, Yizhong Wang, Jiwei Li, Eduard Hovy, Chen Guo

Knowledge-Enhanced Evidence Retrieval for Counterargument Generation (2021.findings-emnlp)

Challenge:	Packing is an optimization technique that optimizes training time and resources by combining different training sequences to fit the model’s maximum input length.
Approach:	They perform extensive comparisons between packing and padding methods, covering datasets ranging from 69K to 1.2M and models from 8B to 70B.
Outcome:	The proposed method has been shown to improve training efficiency while maintaining performance.

Copied to clipboard

Yohan Jo, Haneul Yoo, JinYeong Bak, Alice Oh, Chris Reed, Eduard Hovy

Information Retrieval

Challenge:	Existing models lack the reasoning abilities needed to find complex counterevidence.
Approach:	They propose a natural language inference model that finds counterevidence from diverse sources on the Web.
Outcome:	The proposed model outperforms baseline models for NLI tasks and finds complex counterevidence better.

MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering (2025.findings-acl)

Copied to clipboard

Shuo Yang, Caren Han, Siwen Luo, Eduard Hovy

An Empirical Exploration of Local Ordering Pre-training for Structured Prediction (2020.findings-emnlp)

Challenge:	Existing Large Vision-Language Models (LVLMs) lack integrated commonsense knowledge . lack of integrated common knowledge limits their robustness and accuracy in VQA .
Approach:	They propose a framework to enhance multimodal inference by integrating commonsense reasoning.
Outcome:	MAGIC-VQA improves comprehensive benchmark datasets, surpassing existing models in tasks requiring advanced commonsense reasoning.

Copied to clipboard

Zhisong Zhang, Xiang Kong, Lori Levin, Eduard Hovy

What-if I ask you to explain: Explaining the effects of perturbations in procedural text (2020.findings-emnlp)

Challenge:	Recent studies have shown that pre-training contextualized encoders with language model objectives is effective for structured prediction.
Approach:	They propose a semi-supervised method for pre-training contextualized encoders with language model objectives.
Outcome:	The proposed method is effective on three typical structured prediction tasks in four languages.

Copied to clipboard

Dheeraj Rajagopal, Niket Tandon, Peter Clark, Bhavana Dalvi, Eduard Hovy

Explainability & Interpretability in NLP

Challenge:	QUARTET constructs explanations from paragraphs using procedural text . qartet achieves 18 points better on explanation accuracy compared to strong baselines on a recent process comprehension benchmark.
Approach:	They propose a system that constructs explanations from paragraphs by modeling the explanation task as a multitask learning problem.
Outcome:	The proposed system achieves 18 points better on explanation accuracy compared to strong baselines on a process comprehension benchmark.

What’s the Meaning of Superhuman Performance in Today’s NLU? (2023.acl-long)

Copied to clipboard

Simone Tedeschi, Johan Bos, Thierry Declerck, Jan Hajič, Daniel Hershcovich, Eduard Hovy, Alexander Koller, Simon Krek, Steven Schockaert, Rico Sennrich, Ekaterina Shutova, Roberto Navigli

Transitive Consistency Constrained Learning for Entity-to-Entity Stance Detection (2024.acl-long)

Challenge:	Recent research has focused on developing larger pretrained language models and introducing benchmarks such as SuperGLUE and SQuAD to measure their abilities.
Approach:	They propose to use benchmarks such as SuperGLUE and SQUAD to evaluate PLMs' abilities in language understanding, reasoning, and reading comprehension to assess their performance.
Outcome:	The proposed benchmarks have serious limitations affecting comparison between humans and PLMs and provide recommendations for fairer and more transparent benchmarks.

Copied to clipboard

Haoyang Wen, Eduard Hovy, Alexander Hauptmann

Measuring and Improving Consistency in Pretrained Language Models (2021.tacl-1)

Challenge:	Entity-to-entity stance detection is a streamlined task without the complex dependency structure for structural sentiment analysis.
Approach:	They propose a method that models transitive consistency constraints during training to help train entity-to-entity stance detection models.
Outcome:	The proposed method improves both classification-based and generation-based models while large language models struggle with predicting link direction and neutral labels.

Copied to clipboard

Yanai Elazar, Nora Kassner, Shauli Ravfogel, Abhilasha Ravichander, Eduard Hovy, Hinrich Schütze, Yoav Goldberg

More Identifiable yet Equally Performant Transformers for Text Classification (2021.acl-long)

Challenge:	In this paper, we examine whether pretrained language models are consistent with factual knowledge.
Approach:	They propose a method to improve consistency of pretrained language models . consistency is a desirable property of a good language understanding model, they argue .
Outcome:	The proposed model improves consistency and shows that it is effective.

Copied to clipboard

Rishabh Bhardwaj, Navonil Majumder, Soujanya Poria, Eduard Hovy

Could you give me a hint ? Generating inference graphs for defeasible reasoning (2021.findings-acl)

Challenge:	Current studies prove that attention weights are not unique and therefore unfit for interpretation.
Approach:	They propose a transformer encoder layer that decouples the relationship between key and value vector and provides identifiable weights up to the desired length of the input.
Outcome:	The proposed model is more identifiable than previously thought but still prone to be non-unique attentions that make them unfit for interpretation.

Copied to clipboard

Aman Madaan, Dheeraj Rajagopal, Niket Tandon, Yiming Yang, Eduard Hovy

Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation (2021.findings-acl)

Challenge:	Defeasible reasoning is a mode of reasoning where conclusions can be overturned by taking into account new evidence.
Approach:	They propose to automatically generate inference graphs for a defeasible inference task by transfer learning from a related NLP task.
Outcome:	The proposed method generates meaningful graphs for a defeasible inference task and human accuracy improves by 20%.

Copied to clipboard

Varun Gangal, Harsh Jhamtani, Eduard Hovy, Taylor Berg-Kirkpatrick

Natural Language Interfaces

Challenge:	Prior work has shown that having multiple valid references is important for automated evaluations.
Approach:	They propose a technique for automatically expanding a human generated reference to a set of candidate references.
Outcome:	The proposed method improves correlations between human-generated metrics and human ratings of system outputs.

On the Benefit of Syntactic Supervision for Cross-lingual Transfer in Semantic Role Labeling (2021.emnlp-main)

Copied to clipboard

Data-efficient Active Learning for Structured Prediction with Partial Annotation and Self-Training (2023.findings-emnlp)

Challenge:	Recent advances in neural architectures and pre-trained representations have greatly improved the performance of fully-supervised semantic role labeling (SRL) but there are limitations in the availability of supervised training data.
Approach:	They propose to leverage syntactic dependencies to facilitate cross-lingual transfer by annotating predicate-argument structures in text.
Outcome:	The proposed model can be extended to other languages with limited training data.

Copied to clipboard

Detecting Attackable Sentences in Arguments (2020.emnlp-main)

Challenge:	Structured prediction is a fundamental problem in NLP, wherein the label space consists of complex structured outputs with groups of interdependent variables.
Approach:	They propose a partial annotation approach that selects only the most informative sub-structures for annotation and a method that incorporates the current model's automatic predictions as pseudo-labels for un-annotated sub-structurals.
Outcome:	The proposed approach reduces annotation cost over strong full annotation baselines under a fair comparison scheme that takes reading time into consideration.

Copied to clipboard

Yohan Jo, Seojin Bang, Emaad Manzoor, Eduard Hovy, Chris Reed

Robustness in NLP

Challenge:	Prior work in NLP studies focus on argument quality and making counterarguments toward the main claim, without investigating what parts of an argument are attackable for successful persuasion.
Approach:	They propose to use machine learning to find attackable sentences in online arguments by analyzing driving reasons for attacks and identifying relevant characteristics of sentences.
Outcome:	The proposed model can detect attackable sentences significantly better than baselines and comparably well to laypeople.

Extracting Implicitly Asserted Propositions in Argumentation (2020.emnlp-main)

Copied to clipboard

Yohan Jo, Jacky Visser, Chris Reed, Eduard Hovy

Style is NOT a single variable: Case Studies for Cross-Stylistic Language Understanding (2021.acl-long)

Challenge:	Argumentation is a rhetorical device that asserts propositions implicitly, but few studies have examined the issue.
Approach:	They propose a computational method for extracting propositions that are implicitly asserted in questions, reported speech, and imperatives in argumentation.
Outcome:	The proposed models are based on a corpus of 2016 debates and online commentary.

Copied to clipboard

Dongyeop Kang, Eduard Hovy

Exploring Numeracy in Word Embeddings (P19-1)

Challenge:	a benchmark corpus of text in 15 different styles is used to study stylistic language . a similar benchmark is used for cross-style language understanding .
Approach:	They propose a benchmark corpus that combines existing datasets and collects a new one for cross-style language understanding.
Outcome:	The proposed benchmark corpus contains 15 different styles under four theoretical groupings: figurative, personal, affective, and interpersonal groups.

Copied to clipboard

Aakanksha Naik, Abhilasha Ravichander, Carolyn Rose, Eduard Hovy

Representation Learning

Challenge:	Existing word embeddings are inadequate at capturing numerical properties of numbers.
Approach:	They propose to use word embeddings to capture numerical properties of numbers . they hope to develop methods which better capture numeric properties .
Outcome:	The proposed models lack the ability to capture numeric properties of numbers, the authors show . their findings provide a starting point for the development of better models .

Low-resource Cross-lingual Event Type Detection via Distant Supervision with Minimal Effort (C18-1)

Copied to clipboard

Aldrian Obaja Muis, Naoki Otani, Nidhi Vyas, Ruochen Xu, Yiming Yang, Teruko Mitamura, Eduard Hovy

Multilinguality

Challenge:	Currently, few or no language processing tools or resources exist for most languages . a problem is that there is not enough available training data even in resource-rich languages if the task is complex.
Approach:	They propose to use a bilingual dictionary to train machine learning in a resource-poor language . they also explore adversarial training of bilingual word representations .
Outcome:	The proposed approach gives similar performance in event-type detection tasks.

CHARD: Clinical Health-Aware Reasoning Across Dimensions for Text Generation Models (2023.eacl-main)

Copied to clipboard

Steven Y. Feng, Vivek Khetan, Bogdan Sacaleanu, Anatole Gershman, Eduard Hovy

Nested Named Entity Recognition via Second-best Sequence Learning and Decoding (2020.tacl-1)

Challenge:	Existing studies show that pretrained language models can act as knowledge bases and reason like humans.
Approach:	They propose to use pretrained language models to generate free-flow textual explanations about 52 health conditions across three clinical dimensions.
Outcome:	The proposed model can generate concise and readable text, but can be improved on medical accuracy and QA.

Copied to clipboard

Takashi Shibuya, Eduard Hovy

Erratum: Measuring and Improving Consistency in Pretrained Language Models (2021.tacl-1)

Challenge:	Named entity recognition (NER) is the task of identifying text spans associated with proper names and classifying them according to their semantic class such as person or organization.
Approach:	They propose a method that treats the tag sequence for nested entities as the second best path within the span of their parent entity.
Outcome:	The proposed method achieves F1-scores of 85.82%, 84.34%, and 77.36% on ACE-2004, ACE 2005, and GENIA datasets.

Copied to clipboard

Yanai Elazar, Nora Kassner, Shauli Ravfogel, Abhilasha Ravichander, Eduard Hovy, Hinrich Schütze, Yoav Goldberg

Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes (2021.tacl-1)

Challenge:	During production of this paper, an error was introduced to the formula on the bottom of the right column of page 1020.
Approach:	the formula was changed in the last two terms of the paper .
Outcome:	the correct formula is now available on the web.

Copied to clipboard

Yohan Jo, Seojin Bang, Chris Reed, Eduard Hovy

Text Classification

Challenge:	Recent studies have focused on training complex neural networks on labeled data.
Approach:	They propose to use logical mechanisms to classify argumentative relations without training on labeled data.
Outcome:	The proposed method classifies argumentative relations without training on labeled data significantly better than unsupervised baselines.

One Document, Many Revisions: A Dataset for Classification and Description of Edit Intents (2022.lrec-1)

Copied to clipboard

Dheeraj Rajagopal, Xuchao Zhang, Michael Gamon, Sujay Kumar Jauhar, Diyi Yang, Eduard Hovy

Information Retrieval

Challenge:	Existing methods to understand revisions have failed to provide a deeper understanding of the nature of these edits.
Approach:	They propose to use a Wikipedia revision history dataset to train a classifier that achieves a 90% accuracy in identifying edit intent and a distantly-supervised model that generates .
Outcome:	The proposed model achieves 90% accuracy in identifying edit intent and a best score of 28 ROUGE.

On the Systematicity of Probing Contextualized Word Representations: The Case of Hypernymy in BERT (2020.starsem-1)

Copied to clipboard

Abhilasha Ravichander, Eduard Hovy, Kaheer Suleman, Adam Trischler, Jackie Chi Kit Cheung

An Empirical Investigation of Structured Output Modeling for Graph-based Neural Dependency Parsing (P19-1)

Challenge:	Existing studies have found that BERT can correctly retrieve noun hypernyms in cloze tasks, but this does not correspond to systematic knowledge in BERT.
Approach:	They propose to use BERT to probe for hypernymy knowledge encoded in representations for cloze tasks to find out whether it is systematic or not .
Outcome:	The proposed model can retrieve hypernyms in cloze tasks, but not systematic knowledge in BERT.

Copied to clipboard

Zhisong Zhang, Xuezhe Ma, Eduard Hovy

Syntactic Text Processing

Challenge:	In the past few years, graph-based dependency parsers have led to impressive empirical successes on parsing accuracy.
Approach:	They propose to use a graph-based dependency parser to model global outputs.
Outcome:	The proposed model has been shown to perform better on sentence-level Complete Match metric compared with the previous model.

StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer (2021.naacl-main)

Copied to clipboard

Yiwei Lyu, Paul Pu Liang, Hai Pham, Eduard Hovy, Barnabás Póczos, Ruslan Salakhutdinov, Louis-Philippe Morency

Text Generation

Challenge:	Existing methods for text style transfer focus on individual high-level semantic changes but do not offer fine-grained control of sentence structure, emphasis, and content.
Approach:	They propose a large-scale text style transfer benchmark with 21 fine-grained stylistic changes across atomic lexical, syntactic, semantic, and thematic transfers.
Outcome:	The proposed method allows modeling fine-grained changes as building blocks for more complex, high-level transfers.

Earlier Isn’t Always Better: Sub-aspect Analysis on Corpus and System Biases in Summarization (D19-1)

Copied to clipboard

Taehee Jung, Dongyeop Kang, Lucas Mentch, Eduard Hovy

Summarization

Challenge:	despite recent advances in neural summarization systems, the underlying logic behind the improvements remains unexplored.
Approach:	They define three sub-aspects of summarization: position, importance, diversity . position exhibits substantial bias in news articles, but not with academic papers .
Outcome:	evaluators found that position bias is not present in academic papers and meeting minutes . elucidation provides useful lessons on analyzing summarization datasets .

EVOTOOL: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection (2026.acl-long)

Copied to clipboard

Shuo Yang, Caren Han, Xueqi Ma, Yan Li, Mohammad Reza Ghasemi Madani, Eduard Hovy

Challenge:	Existing approaches to optimize tool-use policies are monolithic and prone to entangling behaviors.
Approach:	They propose a framework that decomposes agent’stool-use policy into four modules and improves them via three mechanisms.
Outcome:	The proposed framework outperforms strong baselines on bothGPT-4.1 and Qwen3-8B while maintaining superior efficiency and transferability.

A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications (N18-1)

Copied to clipboard

Dongyeop Kang, Waleed Ammar, Bhavana Dalvi, Madeleine van Zuylen, Sebastian Kohlmeier, Eduard Hovy, Roy Schwartz

Challenge:	a dataset of 14.7K paper drafts and accept/reject decisions in top-tier venues including ACL, NIPS and ICLR is presented to study peer reviews.
Approach:	They propose to use the dataset to collect peer reviews from top-tier venues including ACL, NIPS and ICLR and to use it to create a dataset of peer reviews for research purposes.
Outcome:	The proposed dataset includes 14.7K paper drafts and accept/reject decisions in top-tier venues including ACL, NIPS and ICLR.

Defining a New NLP Playground (2023.findings-emnlp)

Copied to clipboard

Sha Li, Chi Han, Pengfei Yu, Carl Edwards, Manling Li, Xingyao Wang, Yi Fung, Charles Yu, Joel Tetreault, Eduard Hovy, Heng Ji

Toward Comprehensive Understanding of a Sentiment Based on Human Motives (P19-1)

Challenge:	Recent explosion of performance of large language models (LLMs) has changed the field more abruptly and seismically than any other shift in the field’s 80 year history.
Approach:	They propose 20+ PhD-dissertation-worthy research directions to define a new NLP playground by combining theoretical analysis, new and challenging problems, learning paradigms and interdisciplinary applications.
Outcome:	The proposed research will cover theoretical analysis, new and challenging problems, learning paradigms and interdisciplinary applications.

Copied to clipboard

Naoki Otani, Eduard Hovy

Plan ahead: Self-Supervised Text Planning for Paragraph Completion Task (2020.emnlp-main)

Challenge:	a new study examines the motivations of sentiment holder and their relationship to food . aspects of a sentiment are limited to properties of entities such as the price of food and design of .
Approach:	They define six basic motives that cover a wide range of topics appearing in review texts . they annotate 1,600 texts in restaurant and laptop domains with the motives .
Outcome:	The proposed method improves on annotating 1,600 text with the motives and comparing them to other methods.

Copied to clipboard

Dongyeop Kang, Eduard Hovy

Graph Based Decoding for Event Sequencing and Coreference Resolution (C18-1)

Challenge:	despite the success of contextualized language models, language models cannot capture textual coherence of a long, multi-sentence document.
Approach:	They propose a paragraph completion task that predicts masked sentences in a sentence . they propose SSPlanner that predict what to say first and guides the pretrained model .
Outcome:	The proposed model outperforms baseline generation models on the paragraph completion task in automatic and human evaluation.

Copied to clipboard

Zhengzhong Liu, Teruko Mitamura, Eduard Hovy

PINEAPPLE: Personifying INanimate Entities by Acquiring Parallel Personification Data for Learning Enhanced Generation (2022.coling-1)

Challenge:	In this paper, we study two types of relation between events in text documents.
Approach:	They propose a graph-based decoding algorithm that is applicable to both tasks . they propose ES and EH to solve the event coreference problem .
Outcome:	The proposed decoding algorithm beats a strong temporal-based, oracle-informed baseline.

Copied to clipboard

Sedrick Scott Keh, Kevin Lu, Varun Gangal, Steven Y. Feng, Harsh Jhamtani, Malihe Alikhani, Eduard Hovy

Challenge:	Personifications are figures of speech that endow inanimate entities with properties and actions typically seen as requiring animacy.
Approach:	They propose to use personification data to train a parallel corpus of personifications . they propose to combine personification-related literalizations with automatic ones .
Outcome:	The proposed personification system can generate diverse and creative personifications . it can generate personification-related qualities such as interestingness and animacy .

Think about it! Improving defeasible reasoning by first modeling the question scenario. (2021.emnlp-main)

Copied to clipboard

Aman Madaan, Niket Tandon, Dheeraj Rajagopal, Peter Clark, Yiming Yang, Eduard Hovy

IYKYK: Using language models to decode extremist cryptolects (2026.eacl-long)

Challenge:	Existing literature suggests that a person forms a mental model of the problem scenario before answering questions.
Approach:	They propose to have a model first create a graph of relevant influences and leverage that graph as an additional input when answering a defeasible query.
Outcome:	The proposed model achieves state-of-the-art on three different defeasible reasoning datasets.

Copied to clipboard

Christine de Kock, Arij Riabi, Zeerak Talat, Michael Sejr Schlichtkrull, Pranava Madhyastha, Eduard Hovy

RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning Based on Emotional Information (2025.acl-long)

Challenge:	Extremist groups develop complex in-group language to exclude or mislead outsiders . general purpose LLMs cannot consistently detect or decode extremist language .
Approach:	They evaluate the ability of current language technologies to detect and interpret the cryptolects of two online extremist platforms.
Outcome:	The proposed models can detect and interpret extremist language better than current models.

Copied to clipboard

Zhiwei Liu, Kailai Yang, Qianqian Xie, Christine de Kock, Sophia Ananiadou, Eduard Hovy

On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing (N19-1)

Challenge:	Current methods for cross-domain misinformation detection focus on in-domain tasks and do not incorporate significant sentiment and emotion features.
Approach:	They propose a retrieval augmented (RAG) LLM framework that incorporates affective information into retrieval databases.
Outcome:	The proposed framework improves on three misinformation benchmarks.

Copied to clipboard

Wasi Ahmad, Zhisong Zhang, Xuezhe Ma, Eduard Hovy, Kai-Wei Chang, Nanyun Peng

Cross-Lingual Transfer

Challenge:	Existing studies on crosslingual transfer have focused on word-level information sharing, but words are not independent in sentences; their combinations form larger linguistic units, known as context.
Approach:	They propose to use orderagnostic models to transfer word order to distant languages . they train dependency parsers on an English corpus and evaluate their transfer performance on 30 other languages.
Outcome:	The proposed model performs better on languages with different word orders than on other languages.

Decomposed Opinion Summarization with Verified Aspect-Aware Modules (2025.findings-acl)

Copied to clipboard

Miao Li, Jey Han Lau, Eduard Hovy, Mirella Lapata

Summarization

Challenge:	Existing methods for summarizing opinions from large-scale online reviews are not available for crowdsourcing and are difficult to crowdsource.
Approach:	They propose a domain-agnostic modular approach guided by review aspects to separate tasks of aspect identification, opinion consolidation, and meta-review synthesis to enable greater transparency and ease of inspection.
Outcome:	The proposed approach generates more grounded summaries than baseline models, as verified through automated and human evaluations.

NoiseQA: Challenge Set Evaluation for User-Centric Question Answering (2021.eacl-main)

Copied to clipboard

Abhilasha Ravichander, Siddharth Dalmia, Maria Ryskina, Florian Metze, Eduard Hovy, Alan W Black

Natural Language Interfaces

Challenge:	Question-Answering (QA) systems are deployed in the real world . a lack of research attention has been devoted to studying the issues that arise when people use QA systems.
Approach:	They show that component components that precede an answering engine can introduce varied and considerable sources of error.
Outcome:	The proposed evaluations highlight the need for QA evaluation to expand to consider real-world use.

Article and Comment Frames Shape the Quality of Online Comments (2026.findings-acl)

Copied to clipboard

Matteo Guida, Yulia Otmakhova, Eduard Hovy, Lea Frermann

Linguistics & Cognitive NLP

Challenge:	Recent work has focused on predicting comment toxicity or quality, but it ignores audience reactions.
Approach:	They propose a frame-aware system to mitigate unhealthy discourse . they analysed 1M comments across 2.7K news articles .
Outcome:	The proposed system can mitigate unhealthy discourses by analyzing 1M comments across 2.7K news articles.

PANCETTA: Phoneme Aware Neural Completion to Elicit Tongue Twisters Automatically (2023.eacl-main)

Copied to clipboard

Sedrick Scott Keh, Steven Y. Feng, Varun Gangal, Malihe Alikhani, Eduard Hovy

Syntactic Text Processing

Challenge:	Phonetic difficulty is hard to characterize and can be expressed in tongue twisters through alliteration and homophony.
Approach:	They propose a phoneme-aware neural completion to generate tongue twisters automatically . they leverage phoneme representations to capture phonetic difficulty and train language models .
Outcome:	The proposed language model generates novel, phonetically difficult, fluent, and semantically meaningful tongue twisters on two task settings.

A Two-Step Approach for Implicit Event Argument Detection (2020.acl-main)

Copied to clipboard

Zhisong Zhang, Xiang Kong, Zhengzhong Liu, Xuezhe Ma, Eduard Hovy

Event Extraction

Challenge:	et al., 2015) only consider local arguments in the same sentence of the event trigger.
Approach:	They propose to decompose the implicit event argument detection task into two sub-problems . they propose to use argument head-word detection and head-to-span expansion to reduce the number of candidates.
Outcome:	The proposed model achieves better performance than a strong sequence labeling baseline.

Investigating Robustness of Dialog Models to Popular Figurative Language Constructs (2021.emnlp-main)

Copied to clipboard

Harsh Jhamtani, Varun Gangal, Eduard Hovy, Taylor Berg-Kirkpatrick

Incorporating a Local Translation Mechanism into Non-autoregressive Translation (2020.emnlp-main)

Challenge:	Existing dialog models are unable to handle popular figurative language constructs like metaphor and simile when faced with dialog contexts containing figurativ language.
Approach:	They propose lightweight solutions to help existing dialog models become more robust to figurative language by simply using an external resource to translate figurativ language to literal (non-figurative) forms while preserving the meaning to the best extent possible.
Outcome:	The proposed models show large drops in performance when faced with dialog contexts consisting of figurative language compared to contexts without figurativ language .

Copied to clipboard

Xiang Kong, Zhisong Zhang, Eduard Hovy

Machine Translation

Challenge:	Existing methods to capture local dependencies among output tokens are not efficient, causing errors of repeated translation.
Approach:	They propose a local autoregressive translation mechanism that predicts a short sequence of tokens for each target decoding position instead of one token.
Outcome:	Empirical results show that the proposed method achieves comparable or better performance with fewer decoding iterations, bringing a 2.5x speedup.

Copied to clipboard

Salvador Medina Maza, Evangelia Spiliopoulou, Eduard Hovy, Alexander Hauptmann

Text Classification

Challenge:	Social media has become an important tool to share information about crisis events such as natural disasters and mass attacks.
Approach:	They propose to train an adversarial neural model to remove latent event-specific biases and improve the performance on tweet importance classification.
Outcome:	The proposed model removes event-specific biases and improves on tweet importance classification.

Automatic Event Salience Identification (D18-1)

Copied to clipboard

Zhengzhong Liu, Chenyan Xiong, Teruko Mitamura, Eduard Hovy

Challenge:	Existing models for analyzing salience of discourse units are inadequate . authors propose two saliency detection models based on discourse relations .
Approach:	They propose two salience detection models based on discourse relations that capture complex interactions between discourse units.
Outcome:	The proposed models outperform the strong frequency baseline and improve the feature based model by a large margin.

Iterative Search for Weakly Supervised Semantic Parsing (N19-1)

Copied to clipboard

Pradeep Dasigi, Matt Gardner, Shikhar Murty, Luke Zettlemoyer, Eduard Hovy

Definition Frames: Using Definitions for Hybrid Concept Representations (2020.coling-main)

Challenge:	Recent work has focused on training semantic parsers via weak supervision from denotations alone.
Approach:	They propose an iterative training algorithm that alternates between searching for consistent logical forms and maximizing the marginal likelihood of the retrieved ones.
Outcome:	The proposed algorithm outperforms the previous best systems on WikiTableQuestions and Cornell Natural Language Visual Reasoning (NLVR) iteratively train models that provide guidance to subsequent models to search for logical forms of increasing complexity, thus dealing with spuriousness.

Copied to clipboard

Evangelia Spiliopoulou, Artidoro Pagnoni, Eduard Hovy

Explainability & Interpretability in NLP

Challenge:	a new hybrid representation is proposed that encodes semantic information extracted from definitions.
Approach:	They propose a matrix distributed representation extracted from definitions where each dimension is semantically interpretable.
Outcome:	The proposed representations have competitive performance with other distributional semantic approaches on word similarity tasks.

FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow (D19-1)

Copied to clipboard

Xuezhe Ma, Chunting Zhou, Xian Li, Graham Neubig, Eduard Hovy

Text Generation

Challenge:	Neural sequence-to-sequence models are autoregressive, meaning they factor the joint probability of the output sequence into the product of probabilities over the next to-ken.
Approach:	They propose a non-autoregressive sequence generation model using latent variables . they use generative flow to model complex distributions using neural networks .
Outcome:	The proposed model performs comparable to state-of-the-art models and has constant decoding time w.r.t the sequence length.

Let’s Make Your Request More Persuasive: Modeling Persuasive Strategies via Semi-Supervised Neural Nets on Crowdfunding Platforms (N19-1)

Copied to clipboard

Diyi Yang, Jiaao Chen, Zichao Yang, Dan Jurafsky, Eduard Hovy

Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance? (2021.eacl-main)

Challenge:	Existing models can't quantify persuasiveness of requests or extract successful persuasive strategies.
Approach:	They propose a semi-supervised hierarchical neural network model to quantify persuasiveness and identify persuasive strategies in advocacy requests.
Outcome:	The proposed method outperforms baseline models and offers increased interpretability of persuasive speech.

Copied to clipboard

Abhilasha Ravichander, Yonatan Belinkov, Eduard Hovy

Textual Inference

Challenge:	Neural models have established state-of-the-art performance on several NLP benchmarks, but little is understood about the mechanisms by which they operate.
Approach:	They examine the probing paradigm through a set of controlled synthetic tasks and show that pretrained word embeddings play a considerable role in encoding these properties rather than the training task itself.
Outcome:	The proposed model can encode linguistic properties above chance-level even when distributed in the data as random noise, reversing the interpretation of absolute claims on probing tasks.

Stack-Pointer Networks for Dependency Parsing (P18-1)

Copied to clipboard

Xuezhe Ma, Zecong Hu, Jingzhou Liu, Nanyun Peng, Graham Neubig, Eduard Hovy

Syntactic Text Processing

Challenge:	Existing approaches to dependency parsing are local and greedy transitionbased . StackPtr parsers use the information of whole sentences and previously derived subtree structures .
Approach:	They propose a stack-pointer network-based dependency parser that reads whole sentence and builds dependency tree top-down in a depth-first fashion.
Outcome:	The proposed model reads and encodes whole sentence, then builds dependency tree top-down (from root-to-leaf) in a depth-first fashion.

A Survey of Data Augmentation Approaches for NLP (2021.findings-acl)

Copied to clipboard

Steven Y. Feng, Varun Gangal, Jason Wei, Sarath Chandar, Soroush Vosoughi, Teruko Mitamura, Eduard Hovy

Word Embedding-Based Automatic MT Evaluation Metric using Word Position Information (N19-1)

Challenge:	Data augmentation is a field of research that has been underexplored due to the discrete nature of language data.
Approach:	They present a comprehensive survey of data augmentation for NLP by summarizing the literature in a structured manner.
Outcome:	The proposed methods are used for popular NLP applications and tasks and highlight current challenges and directions for future research.

Copied to clipboard

Hiroshi Echizen’ya, Kenji Araki, Eduard Hovy

Representation Learning

Challenge:	Existing evaluation metrics for machine translation are difficult to address word meaning because it is a surface-level metric.
Approach:	They propose to use word embeddings, sentence-level tf-idf, and cosine similarity between two word embeds as features, weight, and the distance between two features as features.
Outcome:	The proposed metric can evaluate machine translation based on word meaning . it achieves highest correlation with human judgment among several representative metrics.

A Survey of Active Learning for Natural Language Processing (2022.emnlp-main)

Copied to clipboard

A Textual Dataset for Situated Proactive Response Selection (2023.acl-long)

Low-Resource NLP

Challenge:	Existing literature surveys on active learning for NLP are too specific or too general, covering deep active learning.
Approach:	They propose to use active learning to improve model learning and annotation cost for NLP problems.
Outcome:	The proposed approach is based on a large dataset of data-driven machine learning models.

Copied to clipboard

Naoki Otani, Jun Araki, HyeongSik Kim, Eduard Hovy

Natural Language Interfaces

Challenge:	Recent data-driven conversational models can return fluent, consistent, and informative responses to many kinds of requests and utterances in task-oriented scenarios.
Approach:	They propose a task of proactive response selection based on situational information and a dataset of 1.7k English conversation examples that include situational background information and for each conversation a set of responses.
Outcome:	The proposed model can only provide fluent, consistent, and informative responses to a set of 1.7k English conversation examples and is not easy to perform for strong neural models.

Towards Open-Domain Twitter User Profile Inference (2023.findings-acl)

Copied to clipboard

Haoyang Wen, Zhenxin Xiao, Eduard Hovy, Alexander Hauptmann

Challenge:	Existing approaches to user profile inference focus on limited attributes and can reveal users' private information.
Approach:	They propose a prompt-based generation method which can infer values implicitly mentioned in Twitter user profiles.
Outcome:	The proposed method can infer more comprehensive user profiles than baseline extraction-based methods, but limitations remain to be applied for real-world use.

Large-scale Cloze Test Dataset Created by Teachers (D18-1)

Copied to clipboard

Qizhe Xie, Guokun Lai, Zihang Dai, Eduard Hovy

Challenge:	Existing cloze tests are used to evaluate language proficiency in language exams, but they are not yet available.
Approach:	They propose to create a large-scale human-created cloze test dataset CLOTH, which contains questions used in middle-school and high-school language exams.
Outcome:	The proposed dataset outperforms existing models and shows that humans outperformed existing models by a significant margin.

AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples (P18-1)

Copied to clipboard

Dongyeop Kang, Tushar Khot, Ashish Sabharwal, Eduard Hovy