NAACL 2022 Accepted Papers

The full list of 705 papers accepted at NAACL 2022 (North American Chapter of the Association for Computational Linguistics). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

1. Learning To Retrieve Prompts for In-Context LearningLong700 citations
2. FNet: Mixing Tokens with Fourier TransformsLong646 citations
3. MetaICL: Learning to Learn In ContextLong510 citations
4. ColBERTv2: Effective and Efficient Retrieval via Lightweight Late InteractionLong497 citations
5. Do Prompt-Based Models Really Understand the Meaning of Their Prompts?Long405 citations
6. Symbolic Knowledge Distillation: from General Language Models to Commonsense ModelsLong349 citations
7. LongT5: Efficient Text-To-Text Transformer for Long SequencesFindings344 citations
8. Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language DetectionLong289 citations
9. DiffCSE: Difference-based Contrastive Learning for Sentence EmbeddingsLong241 citations
10. TRUE: Re-evaluating Factual Consistency EvaluationLong239 citations
11. QAFactEval: Improved QA-Based Factual Consistency Evaluation for SummarizationLong211 citations
12. Template-free Prompt Tuning for Few-shot NERLong207 citations
13. On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?Long193 citations
14. BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in BanglaFindings190 citations
15. DEGREE: A Data-Efficient Generation-Based Event Extraction ModelLong185 citations
16. KAT: A Knowledge Augmented Transformer for Vision-and-LanguageLong185 citations
17. NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead HeuristicsLong182 citations
18. GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense RetrievalLong177 citations
19. Two Contrasting Data Annotation Paradigms for Subjective NLP TasksLong175 citations
20. On Transferability of Prompt Tuning for Natural Language ProcessingLong161 citations
21. Reframing Human-AI Collaboration for Generating Free-Text ExplanationsLong161 citations
22. Textless Speech-to-Speech Translation on Real DataLong157 citations
23. A Survey on Stance Detection for Mis- and Disinformation IdentificationFindings155 citations
24. QuALITY: Question Answering with Long Input Texts, Yes!Long149 citations
25. FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing TasksFindings147 citations
26. Re2G: Retrieve, Rerank, GenerateLong145 citations
27. SSEGCN: Syntactic and Semantic Enhanced Graph Convolutional Network for Aspect-based Sentiment AnalysisLong145 citations
28. Measure and Improve Robustness in NLP Models: A SurveyLong141 citations
29. Good Visual Guidance Make A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation ExtractionFindings138 citations
30. Lifelong Pretraining: Continually Adapting Language Models to Emerging CorporaLong138 citations
31. COGMEN: COntextualized GNN based Multimodal Emotion recognitioNLong137 citations
32. UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question AnsweringFindings137 citations
33. DEMix Layers: Disentangling Domains for Modular Language ModelingLong133 citations
34. Measuring Fairness with Biased Rulers: A Comparative Study on Bias Metrics for Pre-trained Language ModelsLong127 citations
35. Few-Shot Self-Rationalization with Natural Language PromptsFindings121 citations
36. On the Use of Bert for Automated Essay Scoring: Joint Learning of Multi-Scale Essay RepresentationLong108 citations
37. ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity LinkingIndustry102 citations
38. SKILL: Structured Knowledge Infusion for Large Language ModelsLong100 citations
39. CoMPM: Context Modeling with Speaker’s Pre-trained Memory Tracking for Emotion Recognition in ConversationLong99 citations
40. Fine-grained Image Captioning with CLIP RewardFindings98 citations
41. On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language ModelLong98 citations
42. MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error CorrectionLong97 citations
43. Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for TopicsLong96 citations
44. CLMLF:A Contrastive Learning and Multi-Layer Fusion Method for Multimodal Sentiment DetectionFindings93 citations
45. Cross-modal Contrastive Learning for Speech TranslationLong93 citations
46. Time Waits for No One! Analysis and Challenges of Temporal MisalignmentLong93 citations
47. MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem SolvingFindings91 citations
48. Exploring the Universal Vulnerability of Prompt-based Learning ParadigmFindings90 citations
49. Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP ModelsFindings89 citations
50. Quality-Aware Decoding for Neural Machine TranslationLong87 citations
51. WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language modelsLong86 citations
52. Benchmarking Intersectional Biases in NLPLong85 citations
53. GenIE: Generative Information ExtractionLong84 citations
54. JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question AnsweringLong84 citations
55. POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance DetectionFindings83 citations
56. A Study of the Attention Abnormality in Trojaned BERTsLong81 citations
57. MultiVerS: Improving scientific claim verification with weak supervision and full-document contextFindings81 citations
58. Triggerless Backdoor Attack for NLP Tasks with Clean LabelsLong81 citations
59. Improving Compositional Generalization with Latent Structure and Data AugmentationLong80 citations
60. Learning Rich Representation of Keyphrases from TextFindings79 citations
61. SkillSpan: Hard and Soft Skill Extraction from English Job PostingsLong76 citations
62. Cross-Domain Detection of GPT-2-Generated Technical TextLong75 citations
63. Testing the Ability of Language Models to Interpret Figurative LanguageLong75 citations
64. OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question AnsweringLong74 citations
65. Hierarchical Transformers Are More Efficient Language ModelsFindings73 citations
66. All You May Need for VQA are Image CaptionsLong72 citations
67. Few-Shot Semantic Parsing with Language Models Trained on CodeLong72 citations
68. Great Power, Great Responsibility: Recommendations for Reducing Energy for Training Language ModelsFindings72 citations
69. CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuningLong71 citations
70. Detect Rumors in Microblog Posts for Low-Resource Domains via Adversarial Contrastive LearningFindings71 citations
71. Gender Bias in Masked Language Models for Multiple LanguagesLong71 citations
72. A Two-Stream AMR-enhanced Model for Document-level Event Argument ExtractionLong70 citations
73. FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive SummarizationLong70 citations
74. Less is More: Learning to Refine Dialogue History for Personalized Dialogue GenerationLong69 citations
75. Selective Differential Privacy for Language ModelingLong69 citations
76. Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-Based HateLong68 citations
77. Delving Deep into Regularity: A Simple but Effective Method for Chinese Named Entity RecognitionFindings67 citations
78. SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation ExtractionLong67 citations
79. An Enhanced Span-based Decomposition Method for Few-Shot Sequence LabelingLong66 citations
80. BlonDe: An Automatic Evaluation Metric for Document-level Machine TranslationLong66 citations
81. ConfliBERT: A Pre-trained Language Model for Political Conflict and ViolenceLong64 citations
82. MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided AdaptationLong64 citations
83. SemAttack: Natural Textual Attacks via Different Semantic SpacesFindings63 citations
84. Efficient Hierarchical Domain Adaptation for Pretrained Language ModelsLong62 citations
85. Evidentiality-guided Generation for Knowledge-Intensive NLP TasksLong62 citations
86. TaCL: Improving BERT Pre-training with Token-aware Contrastive LearningFindings62 citations
87. Temporal Attention for Language ModelsFindings62 citations
88. Can Rationalization Improve Robustness?Long61 citations
89. Domain-matched Pre-training Tasks for Dense RetrievalFindings61 citations
90. In-BoXBART: Get Instructions into Biomedical Multi-Task LearningFindings61 citations
91. Knowledge Inheritance for Pre-trained Language ModelsLong61 citations
92. Knowledge-Grounded Dialogue Generation with a Unified Knowledge RepresentationLong61 citations
93. Aligning Generative Language Models with Human ValuesFindings60 citations
94. FactGraph: Evaluating Factuality in Summarization with Semantic Graph RepresentationsLong60 citations
95. IDPG: An Instance-Dependent Prompt Generation MethodLong59 citations
96. Learning to Retrieve Passages without SupervisionLong59 citations
97. Meta Learning for Natural Language Processing: A SurveyLong57 citations
98. MixQG: Neural Question Generation with Mixed Answer TypesFindings57 citations
99. Theory-Grounded Measurement of U.S. Social Stereotypes in English Language ModelsLong57 citations
100. Transparent Human Evaluation for Image CaptioningLong57 citations
101. Overcoming Catastrophic Forgetting During Domain Adaptation of Seq2seq Language GenerationLong56 citations
102. Diagnosing Vision-and-Language Navigation: What Really MattersLong55 citations
103. Exploring Neural Models for Query-Focused SummarizationFindings55 citations
104. MultiSpanQA: A Dataset for Multi-Span Question AnsweringLong55 citations
105. A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News TranslationLong54 citations
106. Generative Biomedical Entity Linking via Knowledge Base-Guided Pre-training and Synonyms-Aware Fine-tuningLong53 citations
107. SeaD: End-to-end Text-to-SQL Generation with Schema-aware DenoisingFindings53 citations
108. The Limits of Word Level Differential PrivacyFindings53 citations
109. AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP TasksFindings52 citations
110. Hate Speech and Counter Speech Detection: Conversational Context Does MatterLong52 citations
111. MultiCite: Modeling realistic citations requires moving beyond the single-sentence single-label settingLong52 citations
112. Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language ModelsLong51 citations
113. Pretrained Models for Multilingual Federated LearningLong51 citations
114. Challenges in Generalization in Open Domain Question AnsweringFindings50 citations
115. Global Entity Disambiguation with BERTLong50 citations
116. Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance LearningLong50 citations
117. SEQZERO: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot ModelsFindings50 citations
118. Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual AnalysisLong50 citations
119. Towards Efficient NLP: A Standard Evaluation and A Strong BaselineLong50 citations
120. Improving Conversational Recommendation Systems’ Quality with Context-Aware Item Meta-InformationFindings49 citations
121. Learning to Transfer Prompts for Text GenerationLong49 citations
122. MultiNERD: A Multilingual, Multi-Genre and Fine-Grained Dataset for Named Entity Recognition (and Disambiguation)Findings48 citations
123. CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement LearningLong47 citations
124. ITA: Image-Text Alignments for Multi-Modal Named Entity RecognitionLong47 citations
125. Learning to Execute Actions or Ask Clarification QuestionsFindings47 citations
126. Visual Commonsense in Pretrained Unimodal and Multimodal ModelsLong47 citations
127. A Robustly Optimized BMRC for Aspect Sentiment Triplet ExtractionLong46 citations
128. Analyzing Modality Robustness in Multimodal Sentiment AnalysisLong46 citations
129. Context-Aware Abbreviation Expansion Using Large Language ModelsLong46 citations
130. Joint Extraction of Entities, Relations, and Events via Modeling Inter-Instance and Inter-Label DependenciesLong46 citations
131. Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source LearningFindings46 citations
132. Entity Cloze By Date: What LMs Know About Unseen EntitiesFindings45 citations
133. Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in SummarizationLong45 citations
134. KALA: Knowledge-Augmented Language Model AdaptationLong45 citations
135. Socially Aware Bias Measurements for Hindi Language RepresentationsLong45 citations
136. A Generative Language Model for Few-shot Aspect-Based Sentiment AnalysisFindings44 citations
137. Aligning to Social Norms and Values in Interactive NarrativesLong44 citations
138. Entailment Tree Explanations via Iterative Retrieval-Generation ReasonerFindings44 citations
139. Literature-Augmented Clinical Outcome PredictionFindings44 citations
140. When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual TransferLong44 citations
141. CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-CheckingLong43 citations
142. Cross-Domain Classification of Moral ValuesFindings43 citations
143. DocEE: A Large-Scale and Fine-grained Benchmark for Document-level Event ExtractionLong43 citations
144. EmpHi: Generating Empathetic Responses with Human-like IntentsLong43 citations
145. HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation ExtractionLong43 citations
146. Meet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few UtterancesLong43 citations
147. Neural Language Taskonomy: Which NLP Tasks are the most Predictive of fMRI Brain Activity?Long43 citations
148. Contrastive Learning for Prompt-based Few-shot Language LearnersLong42 citations
149. FRUIT: Faithfully Reflecting Updated Information in TextLong42 citations
150. Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document SimilarityLong42 citations
151. Query2Particles: Knowledge Graph Reasoning with Particle EmbeddingsFindings42 citations
152. The Role of Context in Detecting Previously Fact-Checked ClaimsFindings42 citations
153. Analyzing Encoded Concepts in Transformer Language ModelsLong41 citations
154. EmRel: Joint Representation of Entities and Embedded Relations for Multi-triple ExtractionLong41 citations
155. Frustratingly Easy System Combination for Grammatical Error CorrectionLong41 citations
156. RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event ExtractionLong41 citations
157. Re-Examining System-Level Correlations of Automatic Summarization Evaluation MetricsLong41 citations
158. AIT-QA: Question Answering Dataset over Complex Tables in the Airline IndustryIndustry40 citations
159. BAD-X: Bilingual Adapters Improve Zero-Shot Cross-Lingual TransferLong40 citations
160. Bidimensional Leaderboards: Generate and Evaluate Language Hand in HandLong40 citations
161. Learning to repair: Repairing model output errors after deployment using a dynamic memory of feedbackFindings40 citations
162. RESIN-11: Schema-guided Event Prediction for 11 Newsworthy ScenariosSystem Demonstrations40 citations
163. Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics FeaturesLong40 citations
164. ALLSH: Active Learning Guided by Local Sensitivity and HardnessFindings39 citations
165. Models in the Loop: Aiding Crowdworkers with Generative Annotation AssistantsLong39 citations
166. UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment AnalysisLong39 citations
167. CODE-MVP: Learning to Represent Source Code from Multiple Views with Contrastive Pre-TrainingFindings38 citations
168. DUCK: Rumour Detection on Social Media by Modelling User and Comment Propagation NetworksLong38 citations
169. DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue GenerationFindings38 citations
170. EASE: Entity-Aware Contrastive Learning of Sentence EmbeddingLong38 citations
171. Entity Linking via Explicit Mention-Mention Coreference ModelingLong38 citations
172. Generative Cross-Domain Data Augmentation for Aspect and Opinion Co-ExtractionLong38 citations
173. GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in TransformersLong38 citations
174. Informativeness and Invariance: Two Perspectives on Spurious Correlations in Natural LanguageLong38 citations
175. KETOD: Knowledge-Enriched Task-Oriented DialogueFindings38 citations
176. METGEN: A Module-Based Entailment Tree Generation Framework for Answer ExplanationFindings38 citations
177. ProQA: Structural Prompt-based Pre-training for Unified Question AnsweringLong38 citations
178. DialSummEval: Revisiting Summarization Evaluation for DialoguesLong37 citations
179. End-to-end Spoken Conversational Question Answering: Task, Dataset and ModelFindings37 citations
180. How Gender Debiasing Affects Internal Model Representations, and Why It MattersLong37 citations
181. Improving the Faithfulness of Abstractive Summarization via Entity Coverage ControlFindings37 citations
182. MCSE: Multimodal Contrastive Learning of Sentence EmbeddingsLong37 citations
183. Maximum Bayes Smatch Ensemble Distillation for AMR ParsingLong37 citations
184. DISARM: Detecting the Victims Targeted by Harmful MemesFindings36 citations
185. Deconstructing NLG Evaluation: Evaluation Practices, Assumptions, and Their ImplicationsLong36 citations
186. PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early ExitingFindings36 citations
187. TWEETSPIN: Fine-grained Propaganda Detection in Social Media Using Multi-View RepresentationsLong36 citations
188. Counterfactually Augmented Data and Unintended Bias: The Case of Sexism and Hate Speech DetectionLong35 citations
189. Document-Level Relation Extraction with Sentences Importance Estimation and FocusingLong35 citations
190. Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and IsotropizationLong35 citations
191. Imagination-Augmented Natural Language UnderstandingLong35 citations
192. Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented DialogLong35 citations
193. NLU++: A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented DialogueFindings35 citations
194. On the Diversity and Limits of Human ExplanationsLong35 citations
195. PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided MCTS DecodingLong35 citations
196. A Holistic Framework for Analyzing the COVID-19 Vaccine DebateLong34 citations
197. Learning Cross-Lingual IR from an English RetrieverLong34 citations
198. Mapping the Design Space of Human-AI Interaction in Text SummarizationLong34 citations
199. Show, Don’t Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented DialogueLong34 citations
200. A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock PredictionLong33 citations
201. Hyperbolic Relevance Matching for Neural Keyphrase ExtractionLong33 citations
202. Many Hands Make Light Work: Using Essay Traits to Automatically Score EssaysLong33 citations
203. Proposition-Level Clustering for Multi-Document SummarizationLong33 citations
204. Robust Conversational Agents against Imperceptible Toxicity TriggersLong33 citations
205. TVShowGuess: Character Comprehension in Stories as Speaker GuessingLong33 citations
206. Cross-document Misinformation Detection based on Event Graph ReasoningLong32 citations
207. Empathetic Persuasion: Reinforcing Empathy and Persuasiveness in Dialogue SystemsFindings32 citations
208. Exposing the Limits of Video-Text Models through Contrast SetsLong32 citations
209. KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge DistillationFindings32 citations
210. Phrase-level Textual Adversarial Attack with Label PreservationFindings32 citations
211. Provably Confidential Language ModellingLong32 citations
212. Same Neurons, Different Languages: Probing Morphosyntax in Multilingual Pre-trained ModelsLong32 citations
213. Zero-Shot Event Detection Based on Ordered Contrastive Learning and Prompt-Based PredictionFindings32 citations
214. Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge TransferLong31 citations
215. EA2E: Improving Consistency with Event Awareness for Document-Level Argument ExtractionFindings31 citations
216. Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic GraphsLong31 citations
217. ExSum: From Local Explanations to Model UnderstandingLong31 citations
218. Explaining Toxic Text via Knowledge Enhanced Text GenerationLong31 citations
219. Extreme Zero-Shot Learning for Extreme Text ClassificationLong31 citations
220. Features or Spurious Artifacts? Data-centric Baselines for Fair and Robust Hate Speech DetectionLong31 citations
221. Improving In-Context Few-Shot Learning via Self-Supervised TrainingLong31 citations
222. MTG: A Benchmark Suite for Multilingual Text GenerationFindings31 citations
223. On the Limitations of Dataset Balancing: The Lost Battle Against Spurious CorrelationsFindings31 citations
224. Inducing and Using Alignments for Transition-based AMR ParsingLong30 citations
225. Tricks for Training Sparse Translation ModelsLong30 citations
226. Am I Me or You? State-of-the-Art Dialogue Models Cannot Maintain an IdentityFindings29 citations
227. AmbiPun: Generating Humorous Puns with Ambiguous ContextLong29 citations
228. Clues Before Answers: Generation-Enhanced Multiple-Choice QALong29 citations
229. Extracting Temporal Event Relation with Syntax-guided Graph TransformerFindings29 citations
230. FOAM: A Follower-aware Speaker Model For Vision-and-Language NavigationLong29 citations
231. How Conservative are Language Models? Adapting to the Introduction of Gender-Neutral PronounsLong29 citations
232. Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech DetectionLong29 citations
233. NewsEdits: A News Article Revision Dataset and a Novel Document-Level Reasoning ChallengeLong29 citations
234. Relation-Specific Attentions over Entity Mentions for Enhanced Document-Level Relation ExtractionLong29 citations
235. Simple Local Attentions Remain Competitive for Long-Context TasksLong29 citations
236. Towards Process-Oriented, Modular, and Versatile Question Generation that Meets Educational NeedsLong29 citations
237. TreeMix: Compositional Constituency-based Data Augmentation for Natural Language UnderstandingLong29 citations
238. Cross-Lingual Event Detection via Optimized Adversarial TrainingLong28 citations
239. Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic EncryptionLong28 citations
240. Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal MisinformationLong28 citations
241. Unified Semantic Typing with Meaningful Label InferenceLong28 citations
242. Using Natural Sentence Prompts for Understanding Biases in Language ModelsLong28 citations
243. You Don’t Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers’ Private PersonasLong28 citations
244. A Shoulder to Cry on: Towards A Motivational Virtual Assistant for Assuaging Mental AgonyLong27 citations
245. Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot ClassificationLong27 citations
246. BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented DialogFindings27 citations
247. Context-Aware Language Modeling for Goal-Oriented Dialogue SystemsFindings27 citations
248. DISAPERE: A Dataset for Discourse Structure in Peer Review DiscussionsLong27 citations
249. Long Context Question Answering via Supervised Contrastive LearningLong27 citations
250. Optimising Equal Opportunity Fairness in Model TrainingLong27 citations
251. PaddleSpeech: An Easy-to-Use All-in-One Speech ToolkitSystem Demonstrations27 citations
252. PromptGen: Automatically Generate Prompts using Generative ModelsFindings27 citations
253. Quiz Design Task: Helping Teachers Create Quizzes with Automated Question GenerationFindings27 citations
254. Semantic Diversity in Dialogue with Natural Language InferenceLong27 citations
255. StATIK: Structure and Text for Inductive Knowledge Graph CompletionFindings27 citations
256. When a sentence does not introduce a discourse entity, Transformer-based models still sometimes refer to itLong27 citations
257. Adaptable AdaptersLong26 citations
258. Crossroads, Buildings and Neighborhoods: A Dataset for Fine-grained Location RecognitionLong26 citations
259. LUNA: Learning Slot-Turn Alignment for Dialogue State TrackingLong26 citations
260. On Measuring Social Biases in Prompt-Based Multi-Task LearningFindings26 citations
261. RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge DistillationFindings26 citations
262. What do tokens know about their characters and how do they know it?Long26 citations
263. Causal Distillation for Language ModelsLong25 citations
264. Commonsense and Named Entity Aware Knowledge Grounded Dialogue GenerationLong25 citations
265. Hero-Gang Neural Model For Named Entity RecognitionLong25 citations
266. KCD: Knowledge Walks and Textual Cues Enhanced Political Perspective Detection in News MediaLong25 citations
267. Probing via PromptingLong25 citations
268. PubHealthTab: A Public Health Table-based Dataset for Evidence-based Fact CheckingFindings25 citations
269. RCL: Relation Contrastive Learning for Zero-Shot Relation ExtractionFindings25 citations
270. SwahBERT: Language Model of SwahiliLong25 citations
271. VGNMN: Video-grounded Neural Module Networks for Video-Grounded Dialogue SystemsLong25 citations
272. Yes, No or IDK: The Challenge of Unanswerable Yes/No QuestionsLong25 citations
273. A Balanced Data Approach for Evaluating Cross-Lingual Transfer: Mapping the Linguistic Blood BankLong24 citations
274. Cryptocurrency Bubble Detection: A New Stock Market Dataset, Financial Task & Hyperbolic ModelsLong24 citations
275. Learn from Relation Information: Towards Prototype Representation Rectification for Few-Shot Relation ExtractionFindings24 citations
276. Machine-in-the-Loop Rewriting for Creative Image CaptioningLong24 citations
277. One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive TranslationLong24 citations
278. Persona-Guided Planning for Controlling the Protagonist’s Persona in Story GenerationLong24 citations
279. Cross-Lingual Cross-Modal Consolidation for Effective Multilingual Video Corpus Moment RetrievalFindings23 citations
280. DREAM: Improving Situational QA by First Elaborating the SituationLong23 citations
281. Domain-Oriented Prefix-Tuning: Towards Efficient and Generalizable Fine-tuning for Zero-Shot Dialogue SummarizationLong23 citations
282. Dynamic Gazetteer Integration in Multilingual Models for Cross-Lingual and Cross-Domain Named Entity RecognitionLong23 citations
283. Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text GenerationLong23 citations
284. ID10M: Idiom Identification in 10 LanguagesFindings23 citations
285. Improving Entity Disambiguation by Reasoning over a Knowledge BaseLong23 citations
286. Intent Detection and Discovery from User Logs via Deep Semi-Supervised Contrastive ClusteringLong23 citations
287. MM-Claims: A Dataset for Multimodal Claim Detection in Social MediaFindings23 citations
288. Measuring and Improving Compositional Generalization in Text-to-SQL via Component AlignmentFindings23 citations
289. Multi-Hop Open-Domain Question Answering over Structured and Unstructured KnowledgeFindings23 citations
290. PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence PretrainingLong23 citations
291. Target-Guided Dialogue Response Generation Using Commonsense and Data AugmentationFindings23 citations
292. What company do words keep? Revisiting the distributional semantics of J.R. Firth & Zellig HarrisLong23 citations
293. textless-lib: a Library for Textless Spoken Language ProcessingSystem Demonstrations23 citations
294. A Dataset for N-ary Relation Extraction of Drug CombinationsLong22 citations
295. A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment ConflictFindings22 citations
296. A Label-Aware Autoregressive Framework for Cross-Domain NERFindings22 citations
297. Beyond Emotion: A Multi-Modal Dataset for Human Desire UnderstandingLong22 citations
298. Few-shot Subgoal Planning with Language ModelsLong22 citations
299. Improving Multi-Document Summarization through Referenced Flexible Extraction with Credit-AwarenessLong22 citations
300. LEA: Meta Knowledge-Driven Self-Attentive Document Embedding for Few-Shot Text ClassificationLong22 citations
301. Learning Dialogue Representations from Consecutive UtterancesLong22 citations
302. Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of TokensLong22 citations
303. On the Use of External Data for Spoken Named Entity RecognitionLong22 citations
304. Prompt Augmented Generative Replay via Supervised Contrastive Learning for Lifelong Intent DetectionFindings22 citations
305. Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous PromptsLong22 citations
306. User-Centric Gender RewritingLong22 citations
307. User-Driven Research of Medical Note Generation SoftwareLong22 citations
308. AcTune: Uncertainty-Based Active Self-Training for Active Fine-Tuning of Pretrained Language ModelsLong21 citations
309. Analytical Reasoning of TextFindings21 citations
310. Aspect Is Not You Need: No-aspect Differential Sentiment Framework for Aspect-based Sentiment AnalysisLong21 citations
311. Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between UtterancesLong21 citations
312. From spoken dialogue to formal summary: An utterance rewriting for dialogue summarizationLong21 citations
313. Guiding Visual Question GenerationLong21 citations
314. Label Anchored Contrastive Learning for Language UnderstandingLong21 citations
315. Nearest Neighbor Knowledge Distillation for Neural Machine TranslationLong21 citations
316. Towards Computationally Feasible Deep Active LearningFindings21 citations
317. Training Mixed-Domain Translation Models via Federated LearningLong21 citations
318. Boosted Dense RetrieverLong20 citations
319. CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to FormalityFindings20 citations
320. Database Search Results Disambiguation for Task-Oriented Dialog SystemsLong20 citations
321. Event Schema Induction with Double Graph AutoencodersLong20 citations
322. Exploring the Role of Task Transferability in Large-Scale Multi-Task LearningLong20 citations
323. Go Back in Time: Generating Flashbacks in Stories with Event Temporal PromptsLong20 citations
324. Investigating Crowdsourcing Protocols for Evaluating the Factual Consistency of SummariesLong20 citations
325. LMTurk: Few-Shot Learners as Crowdsourcing Workers in a Language-Model-as-a-Service FrameworkFindings20 citations
326. Learn To Remember: Transformer with Recurrent Memory for Document-Level Machine TranslationFindings20 citations
327. MOVER: Mask, Over-generate and Rank for Hyperbole GenerationLong20 citations
328. Robust Self-Augmentation for Named Entity Recognition with Meta ReweightingLong20 citations
329. SUBS: Subtree Substitution for Compositional Semantic ParsingLong20 citations
330. Semantically Informed Slang InterpretationLong20 citations
331. An End-to-End Dialogue Summarization System for Sales CallsIndustry19 citations
332. BLINK with Elasticsearch for Efficient Entity Linking in Business ConversationsIndustry19 citations
333. DocTime: A Document-level Temporal Dependency Graph ParserLong19 citations
334. Domain Confused Contrastive Learning for Unsupervised Domain AdaptationLong19 citations
335. Dual-Channel Evidence Fusion for Fact Verification over Texts and TablesLong19 citations
336. Early Rumor Detection Using Neural Hawkes Process with a New Benchmark DatasetLong19 citations
337. KroneckerBERT: Significant Compression of Pre-trained Language Models Through Kronecker Decomposition and Knowledge DistillationLong19 citations
338. Non-Autoregressive Machine Translation: It’s Not as Fast as it SeemsLong19 citations
339. OTExtSum: Extractive Text Summarisation with Optimal TransportFindings19 citations
340. Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent ThresholdLong19 citations
341. Sentence-Level Resampling for Named Entity RecognitionLong19 citations
342. Weakly Supervised Text Classification using Supervision Signals from a Language ModelFindings19 citations
343. Data Augmentation for Low-Resource Dialogue SummarizationFindings18 citations
344. Efficient Few-Shot Fine-Tuning for Opinion SummarizationFindings18 citations
345. Improving negation detection with negation-focused pre-trainingLong18 citations
346. MINION: a Large-Scale and Diverse Dataset for Multilingual Event DetectionLong18 citations
347. Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative TrainingFindings18 citations
348. The Why and The How: A Survey on Natural Language Interaction in VisualizationLong18 citations
349. Towards Open-Domain Topic ClassificationSystem Demonstrations18 citations
350. ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRsFindings17 citations
351. An Exploration of Post-Editing Effectiveness in Text SummarizationLong17 citations
352. Bi-SimCut: A Simple Strategy for Boosting Neural Machine TranslationLong17 citations
353. Consistency Training with Virtual Adversarial Discrete PerturbationLong17 citations
354. Denoising Neural Network for News Recommendation with Positive and Negative Implicit FeedbackFindings17 citations
355. Explore More Guidance: A Task-aware Instruction Network for Sign Language Translation Enhanced with Data AugmentationFindings17 citations
356. Identifying Implicitly Abusive Remarks about Identity Groups using a Linguistically Informed ApproachLong17 citations
357. Improving Few-Shot Relation Classification by Prototypical Representation Learning with Definition TextFindings17 citations
358. Mitigating Toxic Degeneration with Empathetic Data: Exploring the Relationship Between Toxicity and EmpathyLong17 citations
359. NER-MQMRC: Formulating Named Entity Recognition as Multi Question Machine Reading ComprehensionIndustry17 citations
360. On Curriculum Learning for Commonsense ReasoningLong17 citations
361. On the Machine Learning of Ethical Judgments from Natural LanguageLong17 citations
362. On the Robustness of Reading Comprehension Models to Entity RenamingLong17 citations
363. Quantifying Language Variation Acoustically with Few ResourcesLong17 citations
364. Shedding New Light on the Language of the Dark WebLong17 citations
365. Towards Debiasing Translation ArtifactsLong17 citations
366. Towards Understanding Large-Scale Discourse Structures in Pre-Trained and Fine-Tuned Language ModelsLong17 citations
367. A Corpus for Understanding and Generating Moral StoriesLong16 citations
368. AnswerSumm: A Manually-Curated Dataset and Pipeline for Answer SummarizationLong16 citations
369. Ask Me Anything in Your Native LanguageLong16 citations
370. CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-TuningIndustry16 citations
371. Disentangled Learning of Stance and Aspect Topics for Vaccine Attitude Detection in Social MediaLong16 citations
372. Incorporating Centering Theory into Neural Coreference ResolutionLong16 citations
373. Language Models for Code-switch Detection of te reo Māori and English in a Low-resource SettingFindings16 citations
374. Modularized Transfer Learning with Multiple Knowledge Graphs for Zero-shot Commonsense ReasoningLong16 citations
375. OPERA: Operation-Pivoted Discrete Reasoning over TextLong16 citations
376. A New Concept of Knowledge based Question Answering (KBQA) System for Multi-hop ReasoningLong15 citations
377. CLEAR: Improving Vision-Language Navigation with Cross-Lingual, Environment-Agnostic RepresentationsFindings15 citations
378. CORWA: A Citation-Oriented Related Work Annotation DatasetLong15 citations
379. CS1QA: A Dataset for Assisting Code-based Question Answering in an Introductory Programming CourseLong15 citations
380. ChapterBreak: A Challenge Dataset for Long-Range Language ModelsLong15 citations
381. Compositional Task-Oriented Parsing as Abstractive Question AnsweringLong15 citations
382. DACSA: A large-scale Dataset for Automatic summarization of Catalan and Spanish newspaper ArticlesLong15 citations
383. Easy and Efficient Transformer: Scalable Inference Solution For Large NLP ModelIndustry15 citations
384. Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text GenerationLong15 citations
385. FAMIE: A Fast Active Learning Framework for Multilingual Information ExtractionSystem Demonstrations15 citations
386. Few-Shot Document-Level Relation ExtractionLong15 citations
387. Great~Truths~are ~Always ~Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained ModelsFindings15 citations
388. Interpretable Proof Generation via Iterative Backward ReasoningLong15 citations
389. Joint Learning-based Heterogeneous Graph Attention Network for Timeline SummarizationLong15 citations
390. LM-CORE: Language Models with Contextually Relevant External KnowledgeFindings15 citations
391. One Size Does Not Fit All: The Case for Personalised Word Complexity ModelsFindings15 citations
392. Political Ideology and Polarization: A Multi-dimensional ApproachLong15 citations
393. Putting the Con in Context: Identifying Deceptive Actors in the Game of MafiaLong15 citations
394. Quantifying Adaptability in Pre-trained Language Models with 500 TasksLong15 citations
395. Recognition of They/Them as Singular Personal Pronouns in Coreference ResolutionLong15 citations
396. ScAN: Suicide Attempt and Ideation Events DatasetLong15 citations
397. Teaching BERT to Wait: Balancing Accuracy and Latency for Streaming Disfluency DetectionLong15 citations
398. Unsupervised Slot Schema Induction for Task-oriented DialogLong15 citations
399. Weakly Supervised Text-to-SQL Parsing through Question DecompositionFindings15 citations
400. A Dog Is Passing Over The Jet? A Text-Generation Dataset for Korean Commonsense Reasoning and EvaluationFindings14 citations
401. CompactIE: Compact Facts in Open Information ExtractionLong14 citations
402. Federated Learning with Noisy User FeedbackLong14 citations
403. Interactive Query-Assisted Summarization via Deep Reinforcement LearningLong14 citations
404. Modeling Multi-Granularity Hierarchical Features for Relation ExtractionLong14 citations
405. Modeling Task Interactions in Document-Level Joint Entity and Relation ExtractionLong14 citations
406. Multimodal Dialogue State TrackingLong14 citations
407. Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation PerformanceLong14 citations
408. PerKGQA: Question Answering over Personalized Knowledge GraphsFindings14 citations
409. Progressive Class Semantic Matching for Semi-supervised Text ClassificationLong14 citations
410. Reference-free Summarization Evaluation via Semantic Correlation and Compression RatioLong14 citations
411. Self-Training with Differentiable TeacherFindings14 citations
412. Unbiased Math Word Problems Benchmark for Mitigating Solving BiasFindings14 citations
413. XLTime: A Cross-Lingual Knowledge Transfer Framework for Temporal Expression ExtractionFindings14 citations
414. CCQA: A New Web-Scale Question Answering Dataset for Model Pre-TrainingFindings13 citations
415. Controllable Sentence Simplification via Operation ClassificationFindings13 citations
416. Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attentionFindings13 citations
417. Event Detection for Suicide UnderstandingFindings13 citations
418. GRAM: Fast Fine-tuning of Pre-trained Language Models for Content-based Collaborative FilteringLong13 citations
419. Generalized Quantifiers as a Source of Error in Multilingual NLU BenchmarksLong13 citations
420. Learning to Embed Multi-Modal Contexts for Situated Conversational AgentsFindings13 citations
421. Modeling Ideological Salience and Framing in Polarized Online Groups with Graph Neural Networks and Structured SparsityFindings13 citations
422. Partner Personas Generation for Dialogue Response GenerationLong13 citations
423. Practice Makes a Solver Perfect: Data Augmentation for Math Word Problem SolversLong13 citations
424. Seed-Guided Topic Discovery with Out-of-Vocabulary SeedsLong13 citations
425. Syn2Vec: Synset Colexification Graphs for Lexical Semantic SimilarityLong13 citations
426. ZS4IE: A toolkit for Zero-Shot Information Extraction with simple VerbalizationsSystem Demonstrations13 citations
427. A Double-Graph Based Framework for Frame Semantic ParsingLong12 citations
428. Dynamic Multistep Reasoning based on Video Scene Graph for Video Question AnsweringLong12 citations
429. EPiDA: An Easy Plug-in Data Augmentation Framework for High Performance Text ClassificationLong12 citations
430. End-to-End Chinese Speaker IdentificationLong12 citations
431. GMN: Generative Multi-modal Network for Practical Document Information ExtractionLong12 citations
432. Medical Coding with Biomedical Transformer Ensembles and Zero/Few-shot LearningIndustry12 citations
433. Multimodal Intent Discovery from Livestream VideosFindings12 citations
434. RoViST: Learning Robust Metrics for Visual StorytellingFindings12 citations
435. A Study of Syntactic Multi-Modality in Non-Autoregressive Machine TranslationLong11 citations
436. Attention Fusion: a light yet efficient late fusion mechanism for task adaptation in NLUFindings11 citations
437. Conceptualizing Treatment Leakage in Text-based Causal InferenceLong11 citations
438. Cooperative Self-training of Machine Reading ComprehensionLong11 citations
439. Document-Level Event Argument Extraction by Leveraging Redundant Information and Closed Boundary LossLong11 citations
440. Forecasting COVID-19 Caseloads Using Unsupervised Embedding Clusters of Social Media PostsLong11 citations
441. HUE: Pretrained Model and Dataset for Understanding Hanja Documents of Ancient KoreaFindings11 citations
442. Jam or Cream First? Modeling Ambiguity in Neural Machine Translation with SCONESLong11 citations
443. Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask TrainingLong11 citations
444. Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language ModelingLong11 citations
445. Make The Most of Prior Data: A Solution for Interactive Text Summarization with Preference FeedbackFindings11 citations
446. Massive-scale Decoding for Text Generation using LatticesLong11 citations
447. Mining Clues from Incomplete Utterance: A Query-enhanced Network for Incomplete Utterance RewritingLong11 citations
448. Multi-Domain Targeted Sentiment AnalysisLong11 citations
449. On Synthetic Data for Back TranslationLong11 citations
450. On the Effectiveness of Sentence Encoding for Intent Detection Meta-LearningLong11 citations
451. Opportunities for Human-centered Evaluation of Machine Translation SystemsFindings11 citations
452. Partial-input baselines show that NLI models can ignore context, but they don’t.Long11 citations
453. Post-Training Dialogue Summarization using Pseudo-ParaphrasingFindings11 citations
454. Probing the Role of Positional Information in Vision-Language ModelsFindings11 citations
455. Residue-Based Natural Language Adversarial Attack DetectionLong11 citations
456. Stylized Knowledge-Grounded Dialogue Generation via Disentangled Template RewritingLong11 citations
457. A Computational Acquisition Model for Multimodal Word CategorizationLong10 citations
458. A Data Cartography based MixUp for Pre-trained Language ModelsLong10 citations
459. An Information-Theoretic Approach and Dataset for Probing Gender Stereotypes in Multilingual Masked Language ModelsFindings10 citations
460. Building Multilingual Machine Translation Systems That Serve Arbitrary XY TranslationsLong10 citations
461. Constraint-based Multi-hop Question Answering with Knowledge GraphIndustry10 citations
462. Contrastive Representation Learning for Cross-Document Coreference Resolution of Events and EntitiesLong10 citations
463. DOCmT5: Document-Level Pretraining of Multilingual Language ModelsFindings10 citations
464. Dangling-Aware Entity Alignment with Mixed High-Order ProximitiesFindings10 citations
465. Diversifying Neural Dialogue Generation via Negative DistillationLong10 citations
466. Easy Adaptation to Mitigate Gender Bias in Multilingual Text ClassificationLong10 citations
467. Explaining Dialogue Evaluation Metrics using Adversarial Behavioral AnalysisLong10 citations
468. Extending Multi-Text Sentence Fusion Resources via Pyramid AnnotationsLong10 citations
469. FPI: Failure Point Isolation in Large-scale Conversational AssistantsIndustry10 citations
470. Instilling Type Knowledge in Language Models via Multi-Task QAFindings10 citations
471. Learning Natural Language Generation with Truncated Reinforcement LearningLong10 citations
472. Modeling Exemplification in Long-form Question Answering via RetrievalLong10 citations
473. Non-Autoregressive Neural Machine Translation with Consistency Regularization Optimized Variational FrameworkLong10 citations
474. Opponent Modeling in Negotiation Dialogues by Related Data AdaptationFindings10 citations
475. Paragraph-based Transformer Pre-training for Multi-Sentence InferenceLong10 citations
476. Representation Learning for Conversational Data using Discourse Mutual Information MaximizationLong10 citations
477. Towards a Progression-Aware Autonomous Dialogue AgentLong10 citations
478. Uncertainty-Aware Cross-Lingual Transfer with Pseudo Partial LabelsFindings10 citations
479. Unsupervised Domain Adaptation for Question Generation with DomainData Selection and Self-trainingFindings10 citations
480. What Makes a Good and Useful Summary? Incorporating Users in Automatic Summarization ResearchLong10 citations
481. When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout ProbesLong10 citations
482. A Framework to Generate High-Quality Datapoints for Multiple Novel Intent DetectionFindings9 citations
483. Batch-Softmax Contrastive Loss for Pairwise Sentence Scoring TasksLong9 citations
484. Beyond Distributional Hypothesis: Let Language Models Learn Meaning-Text CorrespondenceFindings9 citations
485. Bridging the Gap between Training and Inference: Multi-Candidate Optimization for Diverse Neural Machine TranslationFindings9 citations
486. CL-ReLKT: Cross-lingual Language Knowledge Transfer for Multilingual Retrieval Question AnsweringFindings9 citations
487. CRUSH: Contextually Regularized and User anchored Self-supervised Hate speech DetectionFindings9 citations
488. Data Augmentation with Dual Training for Offensive Span DetectionLong9 citations
489. Design Challenges for a Multi-Perspective Search EngineFindings9 citations
490. DocAMR: Multi-Sentence AMR Representation and EvaluationLong9 citations
491. ErAConD: Error Annotated Conversational Dialog Dataset for Grammatical Error CorrectionLong9 citations
492. Explaining Why: How Instructions and User Interfaces Impact Annotator Rationales When Labeling Text DataLong9 citations
493. Fast Bilingual Grapheme-To-Phoneme ConversionIndustry9 citations
494. Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language DescriptionsFindings9 citations
495. Language Model Augmented Monotonic Attention for Simultaneous TranslationLong9 citations
496. Learning Structural Information for Syntax-Controlled Paraphrase GenerationFindings9 citations
497. LiST: Lite Prompted Self-training Makes Parameter-efficient Few-shot LearnersFindings9 citations
498. Low Resource Style Transfer via Domain Adaptive Meta LearningLong9 citations
499. MGIMN: Multi-Grained Interactive Matching Network for Few-shot Text ClassificationLong9 citations
500. Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual ContextFindings9 citations
501. Masked Summarization to Generate Factually Inconsistent Summaries for Improved Factual Consistency CheckingFindings9 citations
502. Multi-Relational Graph Transformer for Automatic Short Answer GradingLong9 citations
503. Natural Language Inference with Self-Attention for Veracity Assessment of Pandemic ClaimsLong9 citations
504. Negative Sample is Negative in Its Own Way: Tailoring Negative Sentences for Image-Text RetrievalFindings9 citations
505. Non-Autoregressive Chinese ASR Error Correction with Phonological TrainingLong9 citations
506. Permutation Invariant Strategy Using Transformer Encoders for Table UnderstandingFindings9 citations
507. QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual ReasoningFindings9 citations
508. Reducing Disambiguation Biases in NMT by Leveraging Explicit Word Sense InformationLong9 citations
509. Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based AttacksFindings9 citations
510. Social Norms Guide Reference ResolutionLong9 citations
511. Text Style Transfer via Optimal TransportLong9 citations
512. The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine TranslationLong9 citations
513. ValCAT: Variable-Length Contextualized Adversarial Transformations Using Encoder-Decoder Language ModelLong9 citations
514. Zero-shot Entity Linking with Less DataFindings9 citations
515. Augmenting Poetry Composition with Verse by VerseIndustry8 citations
516. Bridging the Gap between Language Models and Cross-Lingual Sequence LabelingLong8 citations
517. Combining Humor and Sarcasm for Improving Political Parody DetectionLong8 citations
518. Crake: Causal-Enhanced Table-Filler for Question Answering over Large Scale Knowledge BaseFindings8 citations
519. Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language UnderstandingLong8 citations
520. D2GCLF: Document-to-Graph Classifier for Legal Document ClassificationFindings8 citations
521. DadmaTools: Natural Language Processing Toolkit for Persian LanguageSystem Demonstrations8 citations
522. Dependency Position Encoding for Relation ExtractionFindings8 citations
523. Disentangled Action Recognition with Knowledge BasesLong8 citations
524. ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language ModelsLong8 citations
525. Enhancing Self-Attention with Knowledge-Assisted Attention MapsLong8 citations
526. Exploiting Numerical-Contextual Knowledge to Improve Numerical Reasoning in Question AnsweringFindings8 citations
527. GraphCache: Message Passing as Caching for Sentence-Level Relation ExtractionFindings8 citations
528. Identifying Corporate Credit Risk Sentiments from Financial NewsIndustry8 citations
529. Label Definitions Improve Semantic Role LabelingLong8 citations
530. Label Refinement via Contrastive Learning for Distantly-Supervised Named Entity RecognitionFindings8 citations
531. Learning as Conversation: Dialogue Systems Reinforced for Information AcquisitionLong8 citations
532. Learning to Express in Knowledge-Grounded ConversationLong8 citations
533. NeuS: Neutral Multi-News Summarization for Mitigating Framing BiasLong8 citations
534. Por Qué Não Utiliser Alla Språk? Mixed Training with Gradient Optimization in Few-Shot Cross-Lingual TransferFindings8 citations
535. SentSpace: Large-Scale Benchmarking and Evaluation of Text using Cognitively Motivated Lexical, Syntactic, and Semantic FeaturesSystem Demonstrations8 citations
536. To Answer or Not To Answer? Improving Machine Reading Comprehension Model with Span-based Contrastive LearningFindings8 citations
537. Understand before Answer: Improve Temporal Reading Comprehension via Precise Question UnderstandingLong8 citations
538. What Factors Should Paper-Reviewer Assignments Rely On? Community Perspectives on Issues and Ideals in Conference Peer-ReviewLong8 citations
539. Zero-shot Cross-lingual Conversational Semantic Role LabelingFindings8 citations
540. Automatic Correction of Human TranslationsLong7 citations
541. BitextEdit: Automatic Bitext Editing for Improved Low-Resource Machine TranslationFindings7 citations
542. Collective Relevance Labeling for Passage RetrievalLong7 citations
543. Combating the Curse of Multilinguality in Cross-Lingual WSD by Aligning Sparse Contextualized Word RepresentationsLong7 citations
544. D2U: Distance-to-Uniform Learning for Out-of-Scope DetectionLong7 citations
545. DecBERT: Enhancing the Language Understanding of BERT with Causal Attention MasksFindings7 citations
546. Detecting Narrative Elements in Informational TextFindings7 citations
547. Distantly Supervised Aspect Clustering And Naming For E-Commerce ReviewsIndustry7 citations
548. Do Deep Neural Nets Display Human-like Attention in Short Answer Scoring?Long7 citations
549. Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense KnowledgeLong7 citations
550. Generating Authentic Adversarial Examples beyond Meaning-preserving with Doubly Round-trip TranslationLong7 citations
551. Improve Discourse Dependency Parsing with Contextualized RepresentationsFindings7 citations
552. Lacuna Reconstruction: Self-Supervised Pre-Training for Low-Resource Historical Document TranscriptionFindings7 citations
553. Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical ConstraintsLong7 citations
554. RSTGen: Imbuing Fine-Grained Interpretable Control into Long-FormText GeneratorsLong7 citations
555. Sketching as a Tool for Understanding and Accelerating Self-attention for Long SequencesLong7 citations
556. Syntax Controlled Knowledge Graph-to-Text Generation with Order and Semantic ConsistencyFindings7 citations
557. Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style TransferLong7 citations
558. TurkishDelightNLP: A Neural Turkish NLP ToolkitSystem Demonstrations7 citations
559. A Structured Span SelectorLong6 citations
560. AISFG: Abundant Information Slot Filling GeneratorLong6 citations
561. Abstraction not Memory: BERT and the English Article SystemLong6 citations
562. Capturing Conversational Interaction for Question Answering via Global History ReasoningFindings6 citations
563. Controlled Data Generation via Insertion Operations for NLUIndustry6 citations
564. Developing a Production System for Purpose of Call Detection in Business Phone ConversationsIndustry6 citations
565. Does it Really Generalize Well on Unseen Data? Systematic Evaluation of Relational Triple Extraction MethodsLong6 citations
566. Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGsLong6 citations
567. How to Translate Your Samples and Choose Your Shots? Analyzing Translate-train & Few-shot Cross-lingual TransferFindings6 citations
568. Improving Neural Models for Radiology Report Retrieval with Lexicon-based Automated AnnotationLong6 citations
569. Is “My Favorite New Movie” My Favorite Movie? Probing the Understanding of Recursive Noun PhrasesLong6 citations
570. Knowledge Extraction From Texts Based on WikidataIndustry6 citations
571. Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image RetrievalLong6 citations
572. Learning to Selectively Learn for Weakly Supervised Paraphrase Generation with Model-based Reinforcement LearningLong6 citations
573. On Systematic Style Differences between Unsupervised and Supervised MT and an Application for High-Resource Machine TranslationLong6 citations
574. Quantifying Synthesis and Fusion and their Impact on Machine TranslationLong6 citations
575. Semantic-Preserving Abstractive Text Summarization with Siamese Generative Adversarial NetFindings6 citations
576. TSTR: Too Short to Represent, Summarize with Details! Intro-Guided Extended Summary GenerationLong6 citations
577. Using Paraphrases to Study Properties of Contextual EmbeddingsLong6 citations
578. What do Toothbrushes do in the Kitchen? How Transformers Think our World is StructuredLong6 citations
579. When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?Findings6 citations
580. ”Diversity and Uncertainty in Moderation” are the Key to Data Selection for Multilingual Few-shot TransferFindings6 citations
581. Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue SystemFindings5 citations
582. CTM - A Model for Large-Scale Multi-View Tweet Topic ClassificationIndustry5 citations
583. CoSIm: Commonsense Reasoning for Counterfactual Scene ImaginationLong5 citations
584. CoSe-Co: Text Conditioned Generative CommonSense ContextualizerLong5 citations
585. Disentangling Indirect Answers to Yes-No Questions in Real ConversationsLong5 citations
586. Does Summary Evaluation Survive Translation to Other Languages?Long5 citations
587. Embedding Hallucination for Few-shot Language Fine-tuningLong5 citations
588. Empathic Machines: Using Intermediate Features as Levers to Emulate Emotions in Text-To-Speech SystemsLong5 citations
589. Exact Paired-Permutation Testing for Structured Test StatisticsLong5 citations
590. Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with VAEsLong5 citations
591. Flowstorm: Open-Source Platform with Hybrid Dialogue ArchitectureSystem Demonstrations5 citations
592. Improving Contextual Representation with Gloss Regularized Pre-trainingFindings5 citations
593. Interactive Symbol Grounding with Complex Referential ExpressionsLong5 citations
594. Knowledge extraction from aeronautical messages (NOTAMs) with self-supervised language models for aircraft pilotsIndustry5 citations
595. LaMemo: Language Modeling with Look-Ahead MemoryLong5 citations
596. Lightweight Transformers for Conversational AIIndustry5 citations
597. Long-term Control for Dialogue Generation: Methods and EvaluationLong5 citations
598. Restoring Hebrew Diacritics Without a DictionaryFindings5 citations
599. SETSum: Summarization and Visualization of Student Evaluations of TeachingSystem Demonstrations5 citations
600. Seeing the wood for the trees: a contrastive regularization method for the low-resource Knowledge Base Question AnsweringFindings5 citations
601. TANet: Thread-Aware Pretraining for Abstractive Conversational SummarizationFindings5 citations
602. TEAM: A multitask learning based Taxonomy Expansion approach for Attach and MergeFindings5 citations
603. Temporal Generalization for Spoken Language UnderstandingIndustry5 citations
604. The USMLE® Step 2 Clinical Skills Patient Note CorpusLong5 citations
605. A Question-Answer Driven Approach to Reveal Affirmative Interpretations from Verbal NegationsFindings4 citations
606. A Versatile Adaptive Curriculum Learning Framework for Task-oriented Dialogue Policy LearningFindings4 citations
607. Answer Consolidation: Formulation and BenchmarkingLong4 citations
608. Asynchronous Convergence in Multi-Task Learning via Knowledge Distillation from Converged TasksIndustry4 citations
609. Balancing Multi-Domain Corpora Learning for Open-Domain Response GenerationFindings4 citations
610. BehancePR: A Punctuation Restoration Dataset for Livestreaming Video TranscriptFindings4 citations
611. Disentangling Categorization in Multi-agent Emergent CommunicationLong4 citations
612. Don’t sweat the small stuff, classify the rest: Sample Shielding to protect text classifiers against adversarial attacksLong4 citations
613. EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and IdentificationFindings4 citations
614. Generating Repetitions with Appropriate Repeated WordsLong4 citations
615. Improving Constituent Representation with Hypertree Neural NetworksLong4 citations
616. Intent Discovery for Enterprise Virtual Assistants: Applications of Utterance Embedding and Clustering to Intent MiningIndustry4 citations
617. Jointly Learning Guidance Induction and Faithful Summary Generation via Conditional Variational AutoencodersFindings4 citations
618. Latent Group Dropout for Multilingual and Multidomain Machine TranslationFindings4 citations
619. Locally Aggregated Feature Attribution on Natural Language Model UnderstandingLong4 citations
620. Modal Dependency Parsing via Language Model PrimingLong4 citations
621. Pruning Adatperfusion with Lottery Ticket HypothesisFindings4 citations
622. Self-supervised Product Title Rewrite for Product Listing AdsIndustry4 citations
623. Speeding Up EntmaxFindings4 citations
624. Towards Job-Transition-Tag Graph for a Better Job Title Representation LearningFindings4 citations
625. WiC = TSV = WSD: On the Equivalence of Three Semantic TasksLong4 citations
626. Adversarial Text NormalizationIndustry3 citations
627. Aspect-based Analysis of Advertising Appeals for Search Engine AdvertisingIndustry3 citations
628. CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session DataLong3 citations
629. CIAug: Equipping Interpolative Augmentation with Curriculum LearningLong3 citations
630. Challenging America: Modeling language in longer time scalesFindings3 citations
631. Do Trajectories Encode Verb Meaning?Long3 citations
632. Efficient Constituency Tree based Encoding for Natural Language to Bash TranslationLong3 citations
633. Efficient Learning of Multiple NLP Tasks via Collective Weight Factorization on BERTFindings3 citations
634. Grapheme-to-Phoneme Conversion for Thai using Neural Regression ModelsLong3 citations
635. Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant SupervisionFindings3 citations
636. Learning from Bootstrapping and Stepwise Reinforcement Reward: A Semi-Supervised Framework for Text Style TransferFindings3 citations
637. Low-resource Entity Set Expansion: A Comprehensive Study on User-generated TextFindings3 citations
638. Pathway2Text: Dataset and Method for Biomedical Pathway Description GenerationFindings3 citations
639. Penn-Helsinki Parsed Corpus of Early Modern English: First Parsing Results and AnalysisFindings3 citations
640. RGL: A Simple yet Effective Relation Graph Augmented Prompt-based Tuning Approach for Few-Shot LearningFindings3 citations
641. Scalable and Robust Self-Learning for Skill Routing in Large-Scale Conversational AI SystemsIndustry3 citations
642. Self-Aware Feedback-Based Self-Learning in Large-Scale Conversational AIIndustry3 citations
643. Sort by Structure: Language Model Ranking as Dependency ProbingLong3 citations
644. Specializing Pre-trained Language Models for Better Relational Reasoning via Network PruningFindings3 citations
645. TIE: Topological Information Enhanced Structural Reading Comprehension on Web PagesLong3 citations
646. The Case for a Single Model that can Both Generate Continuations and Fill-in-the-BlankFindings3 citations
647. What Do Users Care About? Detecting Actionable Insights from User FeedbackIndustry3 citations
648. Word Tour: One-dimensional Word Embeddings via the Traveling Salesman ProblemLong3 citations
649. A Self-supervised Joint Training Framework for Document RerankingFindings2 citations
650. All Information is Valuable: Question Matching over Full Information Transmission NetworkFindings2 citations
651. An Item Response Theory Framework for PersuasionFindings2 citations
652. Analyzing the Intensity of Complaints on Social MediaFindings2 citations
653. Are All the Datasets in Benchmark Necessary? A Pilot Study of Dataset Evaluation for Text ClassificationLong2 citations
654. Augmenting Training Data for Massive Semantic Matching Models in Low-Traffic E-commerce StoresIndustry2 citations
655. Cheat Codes to Quantify Missing Source Information in Neural Machine TranslationLong2 citations
656. Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain AdaptationFindings2 citations
657. DynamicTOC: Persona-based Table of Contents for Consumption of Long DocumentsLong2 citations
658. Embarrassingly Simple Performance Prediction for Abductive Natural Language InferenceLong2 citations
659. Even the Simplest Baseline Needs Careful Re-investigation: A Case Study on XML-CNNLong2 citations
660. FAtNet: Cost-Effective Approach Towards Mitigating the Linguistic Bias in Speaker Verification SystemsFindings2 citations
661. FreeTransfer-X: Safe and Label-Free Cross-Lingual Transfer from Off-the-Shelf ModelsFindings2 citations
662. From Cognitive to Computational Modeling: Text-based Risky Decision-Making Guided by Fuzzy Trace TheoryFindings2 citations
663. Harmless Transfer Learning for Item EmbeddingsFindings2 citations
664. Implicit n-grams Induced by RecurrenceLong2 citations
665. Improving Code-Switching Dependency Parsing with Semi-Supervised Auxiliary TasksFindings2 citations
666. Learning Discriminative Representations for Open Relation Extraction with Instance Ranking and Label CalibrationFindings2 citations
667. Learning to Generate Examples for Semantic Processing TasksLong2 citations
668. Masked Part-Of-Speech Model: Does Modeling Long Context Help Unsupervised POS-tagging?Long2 citations
669. Minimally-Supervised Relation Induction from Pre-trained Language ModelFindings2 citations
670. Parameter-efficient Continual Learning Framework in Industrial Real-time Text Classification SystemIndustry2 citations
671. Retrieval Based Response Letter Generation For a Customer Care SettingIndustry2 citations
672. SHARP: Search-Based Adversarial Attack for Structured PredictionFindings2 citations
673. SURF: Semantic-level Unsupervised Reward Function for Machine TranslationLong2 citations
674. Sparse Distillation: Speeding Up Text Classification by Using Bigger Student ModelsLong2 citations
675. SueNes: A Weakly Supervised Approach to Evaluating Single-Document Summarization via Negative SamplingLong2 citations
676. Unsupervised Paraphrasability Prediction for Compound NominalizationsLong2 citations
677. Unsupervised Stem-based Cross-lingual Part-of-Speech Tagging for Morphologically Rich Low-Resource LanguagesLong2 citations
678. WALNUT: A Benchmark on Semi-weakly Supervised Learning for Natural Language UnderstandingLong2 citations
679. What kinds of errors do reference resolution models make and what can we learn from them?Findings2 citations
680. White-box Testing of NLP models with Mask Neuron CoverageFindings2 citations
681. A Human-machine Interface for Few-shot Rule Synthesis for Information ExtractionSystem Demonstrations1 citations
682. Bilingual Tabular Inference: A Case Study on Indic LanguagesLong1 citations
683. CULG: Commercial Universal Language GenerationIndustry1 citations
684. Contrastive Explanations of Text Classifiers as a ServiceSystem Demonstrations1 citations
685. Efficient Semi-supervised Consistency Training for Natural Language UnderstandingIndustry1 citations
686. Explaining the Effectiveness of Multi-Task Learning for Efficient Knowledge Extraction from Spine MRI ReportsIndustry1 citations
687. Exploring the Value of Multi-View Learning for Session-Aware Query RepresentationFindings1 citations
688. LITE: Intent-based Task Representation Learning Using Weak SupervisionLong1 citations
689. Learning the Ordering of Coordinate Compounds and Elaborate Expressions in Hmong, Lahu, and ChineseLong1 citations
690. MuCPAD: A Multi-Domain Chinese Predicate-Argument DatasetLong1 citations
691. Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity MatchingFindings1 citations
692. On the Economics of Multilingual Few-shot Learning: Modeling the Cost-Performance Trade-offs of Machine Translated and Manual DataLong1 citations
693. Q2R: A Query-to-Resolution System for Natural-Language QueriesIndustry1 citations
694. Revisiting Generative Commonsense Reasoning: A Pre-Ordering ApproachFindings1 citations
695. A Timestep aware Sentence Embedding and Acme Coverage for Brief but Informative Title GenerationFindings
696. AB/BA analysis: A framework for estimating keyword spotting recall improvement while maintaining audio privacyIndustry
697. Constraining word alignments with posterior regularization for label transferIndustry
698. Don’t Take It Literally: An Edit-Invariant Sequence Loss for Text GenerationLong
699. Fast and Light-Weight Answer Text Retrieval in Dialogue SystemsIndustry
700. Generic and Trend-aware Curriculum Learning for Relation ExtractionLong
701. Learning to Borrow– Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph CompletionLong
702. Lifting the Curse of Multilinguality by Pre-training Modular TransformersLong
703. Local-to-global learning for iterative training of production SLU models on new featuresIndustry
704. Unsupervised Cross-Lingual Transfer of Structured Predictors without Source DataLong
705. Web-based Annotation Interface for Derivational MorphologySystem Demonstrations

Looking for submission deadlines instead? See the conference deadline calendar.