ACL 2022 Accepted Papers

The full list of 1,031 papers accepted at ACL 2022 (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. TruthfulQA: Measuring How Models Mimic Human FalsehoodsLong1,725 citations
2. GLM: General Language Model Pretraining with Autoregressive Blank InfillingLong1,644 citations
3. P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and TasksShort1,517 citations
4. BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelsShort1,295 citations
5. Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order SensitivityLong1,172 citations
6. Language-agnostic BERT Sentence EmbeddingLong1,081 citations
7. Cross-Task Generalization via Natural Language Crowdsourcing InstructionsLong697 citations
8. UniXcoder: Unified Cross-Modal Pre-training for Code RepresentationLong659 citations
9. Deduplicating Training Data Makes Language Models BetterLong656 citations
10. ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical ReasoningFindings617 citations
11. Knowledge Neurons in Pretrained TransformersLong600 citations
12. Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text ModelsFindings553 citations
13. PPT: Pre-trained Prompt Tuning for Few-shot LearningLong503 citations
14. Unified Structure Generation for Universal Information ExtractionLong484 citations
15. ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech DetectionLong461 citations
16. LinkBERT: Pretraining Language Models with Document LinksLong411 citations
17. Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text ClassificationLong410 citations
18. BBQ: A hand-built bias benchmark for question answeringFindings392 citations
19. Internet-Augmented Dialogue GenerationLong391 citations
20. Generated Knowledge Prompting for Commonsense ReasoningLong361 citations
21. Unsupervised Corpus Aware Language Model Pre-training for Dense Passage RetrievalLong351 citations
22. BRIO: Bringing Order to Abstractive SummarizationLong334 citations
23. SPoT: Better Frozen Model Adaptation through Soft Prompt TransferLong308 citations
24. Beyond Goldfish Memory: Long-Term Open-Domain ConversationLong291 citations
25. LexGLUE: A Benchmark Dataset for Legal Language Understanding in EnglishLong280 citations
26. SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language ProcessingLong271 citations
27. SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language ModelsLong256 citations
28. Structured Pruning Learns Compact and Accurate ModelsLong253 citations
29. Noisy Channel Language Model Prompting for Few-Shot Text ClassificationLong221 citations
30. CBLUE: A Chinese Biomedical Language Understanding Evaluation BenchmarkLong218 citations
31. Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language ModelsFindings215 citations
32. Reframing Instructional Prompts to GPTk’s LanguageFindings215 citations
33. CONTaiNER: Few-Shot Named Entity Recognition via Contrastive LearningLong211 citations
34. An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language ModelsLong208 citations
35. PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document SummarizationLong203 citations
36. UniPELT: A Unified Framework for Parameter-Efficient Language Model TuningLong202 citations
37. Auto-Debias: Debiasing Masked Language Models with Automated Biased PromptsLong199 citations
38. Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue SystemLong197 citations
39. Sequence-to-Sequence Knowledge Graph Completion and Question AnsweringLong191 citations
40. A Recipe for Arbitrary Text Style Transfer with Large Language ModelsShort186 citations
41. Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine TextLong183 citations
42. Direct Speech-to-Speech Translation With Discrete UnitsLong182 citations
43. Data Contamination: From Memorization to ExploitationShort181 citations
44. A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language ModelsLong178 citations
45. An Information-theoretic Approach to Prompt Engineering Without Ground Truth LabelsLong177 citations
46. Packed Levitated Marker for Entity and Relation ExtractionLong172 citations
47. Enhanced Multi-Channel Graph Convolutional Network for Aspect Sentiment Triplet ExtractionLong164 citations
48. RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question AnsweringLong161 citations
49. LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document UnderstandingLong160 citations
50. Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument ExtractionLong159 citations
51. CLIP Models are Few-Shot Learners: Empirical Studies on VQA and Visual EntailmentLong155 citations
52. Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive SummarizationLong152 citations
53. Meta-learning via Language Model In-context TuningLong152 citations
54. Chart-to-Text: A Large-Scale Benchmark for Chart SummarizationLong151 citations
55. Systematic Inequalities in Language Technology Performance across the World’s LanguagesLong146 citations
56. A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text GenerationLong145 citations
57. Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional NetworkLong140 citations
58. ReACC: A Retrieval-Augmented Code Completion FrameworkLong140 citations
59. Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question AnsweringLong140 citations
60. Composable Sparse Fine-Tuning for Cross-Lingual TransferLong139 citations
61. Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge DistillationFindings139 citations
62. SummScreen: A Dataset for Abstractive Screenplay SummarizationLong138 citations
63. Text-Free Prosody-Aware Generative Spoken Language ModelingLong136 citations
64. Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future DirectionsLong136 citations
65. XLM-E: Cross-lingual Language Model Pre-training via ELECTRALong136 citations
66. ReCLIP: A Strong Zero-Shot Baseline for Referring Expression ComprehensionLong135 citations
67. Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text ClassificationLong134 citations
68. MISC: A Mixed Strategy-Aware Model integrating COMET for Emotional Support ConversationLong132 citations
69. Is Attention Explanation? An Introduction to the DebateLong131 citations
70. Boundary Smoothing for Named Entity RecognitionLong130 citations
71. MoEfication: Transformer Feed-forward Layers are Mixtures of ExpertsFindings130 citations
72. KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question AnsweringLong128 citations
73. Debiased Contrastive Learning of Unsupervised Sentence RepresentationsLong124 citations
74. RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet ExtractionFindings124 citations
75. TableFormer: Robust Transformer Modeling for Table-Text EncodingLong124 citations
76. Fully Hyperbolic Neural NetworksLong123 citations
77. Skill Induction and Planning with Latent LanguageLong123 citations
78. KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge BaseLong122 citations
79. Complex Evolutional Pattern Learning for Temporal Knowledge Graph ReasoningShort119 citations
80. Long Time No See! Open-Domain Conversation with Long-Term Persona MemoryFindings118 citations
81. Graph Pre-training for AMR Parsing and GenerationLong116 citations
82. DeepStruct: Pretraining of Language Models for Structure PredictionFindings114 citations
83. Dynamic Prefix-Tuning for Generative Template-based Event ExtractionLong114 citations
84. SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive SummarizationLong114 citations
85. Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training DataLong112 citations
86. Discrete Opinion Tree Induction for Aspect-based Sentiment AnalysisLong111 citations
87. MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual DataLong111 citations
88. Prototypical Verbalizer for Prompt-based Few-shot TuningLong110 citations
89. Do Pre-trained Models Benefit Knowledge Graph Completion? A Reliable Evaluation and a Reasonable ApproachFindings109 citations
90. Enabling Multimodal Generation on CLIP via Vision-Language Knowledge DistillationFindings109 citations
91. MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NERLong109 citations
92. EmoCaps: Emotion Capsule based Model for Conversational Emotion RecognitionFindings108 citations
93. IndicBART: A Pre-trained Model for Indic Natural Language GenerationFindings108 citations
94. SummN: A Multi-Stage Summarization Framework for Long Input Dialogues and DocumentsLong108 citations
95. VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic PhenomenaLong108 citations
96. Vision-Language Pre-Training for Multimodal Aspect-Based Sentiment AnalysisLong108 citations
97. Decomposed Meta-Learning for Few-Shot Named Entity RecognitionFindings107 citations
98. HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language GenerationLong107 citations
99. THE-X: Privacy-Preserving Transformer Inference with Homomorphic EncryptionFindings107 citations
100. Label Semantics for Few Shot Named Entity RecognitionFindings106 citations
101. STEMM: Self-learning with Speech-text Manifold Mixup for Speech TranslationLong106 citations
102. SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative CapabilitiesLong105 citations
103. The Moral Integrity Corpus: A Benchmark for Ethical Dialogue SystemsLong104 citations
104. Sharpness-Aware Minimization Improves Language Model GeneralizationLong103 citations
105. Fantastic Questions and Where to Find Them: FairytaleQA – An Authentic Dataset for Narrative ComprehensionLong102 citations
106. Reinforced Cross-modal Alignment for Radiology Report GenerationFindings102 citations
107. Compression of Generative Pre-trained Language Models via QuantizationLong101 citations
108. NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning TasksLong101 citations
109. Controllable Natural Language Generation with Contrastive PrefixesFindings100 citations
110. On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language RepresentationsShort99 citations
111. FlipDA: Effective and Robust Data Augmentation for Few-Shot LearningLong98 citations
112. One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in IndonesiaLong97 citations
113. Extracting Latent Steering Vectors from Pretrained Language ModelsFindings96 citations
114. Identifying the Human Values behind ArgumentsLong96 citations
115. PromDA: Prompt-based Data Augmentation for Low-Resource NLU TasksLong96 citations
116. BERT Learns to Teach: Knowledge Distillation with Meta LearningLong95 citations
117. Effective Token Graph Modeling using a Novel Labeling Strategy for Structured Sentiment AnalysisLong93 citations
118. Learning to Reason Deductively: Math Word Problem Solving as Complex Relation ExtractionLong93 citations
119. Adaptive Testing and Debugging of NLP ModelsLong92 citations
120. Making Transformers Solve Compositional TasksLong92 citations
121. S2SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL ParsersFindings92 citations
122. Unified Speech-Text Pre-training for Speech Translation and RecognitionLong92 citations
123. Upstream Mitigation Is Not All You Need: Testing the Bias Transfer Hypothesis in Pre-Trained Language ModelsLong92 citations
124. Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NERLong91 citations
125. AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource LanguagesLong90 citations
126. Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD CodingShort90 citations
127. Revisiting Uncertainty-based Query Strategies for Active Learning with TransformersFindings89 citations
128. AraT5: Text-to-Text Transformers for Arabic Language GenerationLong88 citations
129. French CrowS-Pairs: Extending a challenge dataset for measuring social bias in masked language models to a language other than EnglishLong88 citations
130. Zoom Out and Observe: News Environment Perception for Fake News DetectionLong88 citations
131. BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment AnalysisFindings87 citations
132. FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information ExtractionLong87 citations
133. Legal Judgment Prediction via Event Extraction with ConstraintsLong87 citations
134. MINER: Multi-Interest Matching Network for News RecommendationFindings87 citations
135. Adversarial Soft Prompt Tuning for Cross-Domain Sentiment AnalysisLong86 citations
136. JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance DetectionLong86 citations
137. Tailor: Generating and Perturbing Text with Semantic ControlsLong86 citations
138. bert2BERT: Towards Reusable Pretrained Language ModelsLong86 citations
139. Seq2Path: Generating Sentiment Tuples as Paths of a TreeFindings85 citations
140. Contrastive Learning-Enhanced Nearest Neighbor Mechanism for Multi-Label Text ClassificationShort84 citations
141. Generating Data to Mitigate Spurious Correlations in Natural Language Inference DatasetsLong84 citations
142. Incorporating Dynamic Semantics into Pre-Trained Language Model for Aspect-based Sentiment AnalysisFindings84 citations
143. On the Safety of Conversational Models: Taxonomy, Dataset, and BenchmarkFindings84 citations
144. ParaDetox: Detoxification with Parallel DataLong84 citations
145. Evaluating Extreme Hierarchical Multi-label ClassificationLong83 citations
146. The Paradox of the Compositionality of Natural Language: A Neural Machine Translation Case StudyLong83 citations
147. Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage FusionFindings81 citations
148. FiNER: Financial Numeric Entity Recognition for XBRL TaggingLong81 citations
149. Mix and Match: Learning-free Controllable Text Generationusing Energy Language ModelsLong81 citations
150. ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and ClassificationLong80 citations
151. KNN-Contrastive Learning for Out-of-Domain Intent ClassificationLong80 citations
152. XFUND: A Benchmark Dataset for Multilingual Visually Rich Form UnderstandingFindings80 citations
153. Dict-BERT: Enhancing Language Model Pre-training with DictionaryFindings78 citations
154. Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive SummarizationLong78 citations
155. Parallel Instance Query Network for Named Entity RecognitionLong78 citations
156. Prompt-free and Efficient Few-shot Learning with Language ModelsLong78 citations
157. StableMoE: Stable Routing Strategy for Mixture of ExpertsLong78 citations
158. DYLE: Dynamic Latent Extraction for Abstractive Long-Input SummarizationLong77 citations
159. Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of TextFindings77 citations
160. The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell CheckingFindings77 citations
161. LEVEN: A Large-Scale Chinese Legal Event Detection DatasetFindings76 citations
162. Overcoming a Theoretical Limitation of Self-AttentionLong76 citations
163. Rethinking Document-level Neural Machine TranslationFindings76 citations
164. ∞-former: Infinite Memory TransformerLong75 citations
165. DialFact: A Benchmark for Fact-Checking in DialogueLong74 citations
166. Evaluating Factuality in Text SimplificationLong74 citations
167. Compilable Neural Code Generation with Compiler FeedbackFindings73 citations
168. A Closer Look at How Fine-tuning Changes BERTLong72 citations
169. Efficient Classification of Long Documents Using TransformersShort72 citations
170. Your fairness may vary: Pretrained language model fairness in toxic text classificationFindings72 citations
171. Continual Prompt Tuning for Dialog State TrackingLong70 citations
172. Query and Extract: Refining Event Extraction as Type-oriented Binary DecodingFindings70 citations
173. Revisiting Over-Smoothness in Text to SpeechLong70 citations
174. Fast Nearest Neighbor Machine TranslationFindings69 citations
175. A Contrastive Framework for Learning Sentence Representations from Pairwise and Triple-wise Perspective in Angular SpaceLong68 citations
176. Entropy-based Attention Regularization Frees Unintended Bias Mitigation from ListsFindings67 citations
177. M3ED: Multi-modal Multi-scene Multi-label Emotional Dialogue DatabaseLong67 citations
178. New Intent Discovery with Pre-training and Contrastive LearningLong67 citations
179. RotateQVS: Representing Temporal Information as Rotations in Quaternion Vector Space for Temporal Knowledge Graph CompletionLong67 citations
180. Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word ProblemsFindings67 citations
181. Text-to-Table: A New Way of Information ExtractionLong67 citations
182. UniTE: Unified Translation EvaluationLong67 citations
183. Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine TranslationLong66 citations
184. ELLE: Efficient Lifelong Pre-training for Emerging DataFindings66 citations
185. Expanding Pretrained Models to Thousands More Languages via Lexicon-based AdaptationLong66 citations
186. HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure InformationFindings66 citations
187. Improving the Generalizability of Depression Detection by Leveraging Clinical QuestionnairesLong65 citations
188. MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase ExtractionFindings65 citations
189. Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and LanguagesLong65 citations
190. Multi-View Document Representation Learning for Open-Domain Dense RetrievalLong65 citations
191. Nested Named Entity Recognition with Span-level GraphsLong65 citations
192. ExtEnD: Extractive Entity DisambiguationLong64 citations
193. Memorisation versus Generalisation in Pre-trained Language ModelsLong64 citations
194. Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument ExtractionLong64 citations
195. On Vision Features in Multimodal Machine TranslationLong64 citations
196. Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity RecognitionFindings63 citations
197. Generating Scientific Claims for Zero-Shot Scientific Fact CheckingLong63 citations
198. Local Languages, Third Spaces, and other High-Resource ScenariosLong63 citations
199. MarkupLM: Pre-training of Text and Markup Language for Visually Rich Document UnderstandingLong63 citations
200. Problems with Cosine as a Measure of Embedding Similarity for High Frequency WordsShort63 citations
201. xGQA: Cross-Lingual Visual Question AnsweringFindings63 citations
202. MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision ProcessesLong62 citations
203. SafetyKit: First Aid for Measuring Safety in Open-domain Conversational SystemsLong62 citations
204. Understanding Iterative Revision from Human-Written TextLong62 citations
205. KinyaBERT: a Morphology-aware Kinyarwanda Language ModelLong61 citations
206. The AI Doctor Is In: A Survey of Task-Oriented Dialogue Systems for Healthcare ApplicationsLong61 citations
207. FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text ProcessingLong60 citations
208. NoisyTune: A Little Noise Can Help You Finetune Pretrained Language Models BetterShort60 citations
209. UCTopic: Unsupervised Contrastive Learning for Phrase Representations and Topic MiningLong60 citations
210. CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph CompletionLong59 citations
211. OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across LanguagesLong59 citations
212. Probing for the Usage of Grammatical NumberLong59 citations
213. Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised LearningLong59 citations
214. Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLPLong58 citations
215. Challenges and Strategies in Cross-Cultural NLPLong58 citations
216. Consistent Representation Learning for Continual Relation ExtractionFindings57 citations
217. Continual Few-shot Relation Learning via Embedding Space Regularization and Data AugmentationLong57 citations
218. Tackling Fake News Detection by Continually Improving Social Context Representations using Graph Neural NetworksLong57 citations
219. Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response GenerationLong57 citations
220. ASPECTNEWS: Aspect-Oriented Summarization of News DocumentsLong55 citations
221. DoCoGen: Domain Counterfactual Generation for Low Resource Domain AdaptationLong55 citations
222. Graph Enhanced Contrastive Learning for Radiology Findings SummarizationLong55 citations
223. Inferring Rewards from Language in ContextLong55 citations
224. Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial SettingsFindings55 citations
225. Multi-Granularity Structural Knowledge Distillation for Language Model CompressionLong55 citations
226. Multimodal Dialogue Response GenerationLong55 citations
227. Program Transfer for Answering Complex Questions over Knowledge BasesLong55 citations
228. An Investigation of the (In)effectiveness of Counterfactually Augmented DataLong54 citations
229. Detection of Adversarial Examples in Text Classification: Benchmark and Baseline via Robust Density EstimationFindings54 citations
230. How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired AnalysisFindings54 citations
231. Human Evaluation and Correlation with Automatic Metrics in Consultation Note GenerationLong54 citations
232. Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech RecognitionLong54 citations
233. CICERO: A Dataset for Contextualized Commonsense Inference in DialoguesLong53 citations
234. De-Bias for Generative Extraction in Unified NER TaskLong53 citations
235. Multi-Stage Prompting for Knowledgeable Dialogue GenerationFindings53 citations
236. Read before Generate! Faithful Long Form Question Answering with Machine ReadingFindings53 citations
237. Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative StudyFindings53 citations
238. A Comparative Study of Faithfulness Metrics for Model Interpretability MethodsLong52 citations
239. Inducing Positive Perspectives with Text ReframingLong52 citations
240. MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better TranslatorsLong52 citations
241. Quality Controlled Paraphrase GenerationLong52 citations
242. Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine TranslationLong52 citations
243. A Simple yet Effective Relation Information Guided Approach for Few-Shot Relation ExtractionFindings51 citations
244. Cross-Modal Discrete Representation LearningLong51 citations
245. DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response GenerationLong51 citations
246. Dynamic Schema Graph Fusion Network for Multi-Domain Dialogue State TrackingLong51 citations
247. It is AI’s Turn to Ask Humans a Question: Question-Answer Pair Generation for Children’s Story BooksLong51 citations
248. Mitigating Gender Bias in Distilled Language Models via Counterfactual Role ReversalFindings51 citations
249. Token Dropping for Efficient BERT PretrainingLong51 citations
250. Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning SkillsLong51 citations
251. mLUKE: The Power of Entity Representations in Multilingual Pretrained Language ModelsLong51 citations
252. Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer NetworksLong50 citations
253. Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State TrackingFindings50 citations
254. Ensembling and Knowledge Distilling of Large Sequence Taggers for Grammatical Error CorrectionLong50 citations
255. Fine-Grained Controllable Text Generation Using Non-Residual PromptingLong50 citations
256. Improving Time Sensitivity for Question Answering over Temporal Knowledge GraphsLong50 citations
257. Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 LanguagesLong50 citations
258. Continual Sequence Generation with Adaptive Compositional ModulesLong49 citations
259. Few-shot Named Entity Recognition with Self-describing NetworksLong49 citations
260. LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text RetrievalFindings49 citations
261. Things not Written in Text: Exploring Spatial Commonsense from Visual SignalsLong49 citations
262. Uncertainty Estimation of Transformer Predictions for Misclassification DetectionLong49 citations
263. Word Order Does Matter and Shuffled Language Models Know ItLong49 citations
264. Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant RepresentationsFindings49 citations
265. A Model-agnostic Data Manipulation Method for Persona-based Dialogue GenerationLong48 citations
266. From text to talk: Harnessing conversational corpora for humane and diversity-aware language technologyLong48 citations
267. Nested Named Entity Recognition as Latent Lexicalized Constituency ParsingLong48 citations
268. Achieving Reliable Human Assessment of Open-Domain Dialogue SystemsLong47 citations
269. DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and QuantizationShort47 citations
270. Educational Question Generation of Children Storybooks via Question Type Distribution Learning and Event-centric SummarizationLong47 citations
271. HIBRIDS: Attention with Hierarchical Biases for Structure-aware Long Document SummarizationLong47 citations
272. Hypergraph Transformer: Weakly-Supervised Multi-hop Reasoning for Knowledge-based Visual Question AnsweringLong47 citations
273. Revisiting Automatic Evaluation of Extractive Summarization Task: Can We Do Better than ROUGE?Findings47 citations
274. The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems FailLong47 citations
275. A Simple Hash-Based Early Exiting Approach For Language Understanding and GenerationFindings46 citations
276. An Embarrassingly Simple Method to Mitigate Undesirable Properties of Pretrained Language Model TokenizersShort46 citations
277. IMPLI: Investigating NLI Models’ Performance on Figurative LanguageLong46 citations
278. Label Semantic Aware Pre-training for Few-shot Text ClassificationLong46 citations
279. MERIt: Meta-Path Guided Contrastive Learning for Logical ReasoningFindings46 citations
280. Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph AlignmentLong46 citations
281. Open Domain Question Answering with A Unified Knowledge InterfaceLong46 citations
282. When did you become so smart, oh wise one?! Sarcasm Explanation in Multi-modal Multi-party DialoguesLong46 citations
283. An Analysis of Negation in Natural Language Understanding CorporaShort45 citations
284. Ethics Sheets for AI TasksLong45 citations
285. Modular and Parameter-Efficient Multimodal Fusion with PromptingFindings45 citations
286. A Variational Hierarchical Model for Neural Cross-Lingual SummarizationLong44 citations
287. Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence ModelsFindings44 citations
288. HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation ExtractionFindings44 citations
289. Learning Disentangled Textual Representations via Statistical Measures of SimilarityLong44 citations
290. Misinfo Reaction Frames: Reasoning about Readers’ Reactions to News HeadlinesLong44 citations
291. SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety FailuresLong44 citations
292. The Grammar-Learning Trajectories of Neural Language ModelsLong44 citations
293. Coherence boosting: When your pretrained language model is not paying enough attentionLong43 citations
294. Combining Feature and Instance Attribution to Detect ArtifactsFindings43 citations
295. Discriminative Marginalized Probabilistic Neural Method for Multi-Document Summarization of Medical LiteratureLong43 citations
296. Few-Shot Class-Incremental Learning for Named Entity RecognitionLong43 citations
297. Kronecker Decomposition for GPT CompressionShort43 citations
298. Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine TranslationLong43 citations
299. Transkimmer: Transformer Learns to Layer-wise SkimLong43 citations
300. VALUE: Understanding Dialect Disparity in NLULong43 citations
301. Exploring the Impact of Negative Samples of Contrastive Learning: A Case Study of Sentence EmbeddingFindings42 citations
302. GL-CLeF: A Global–Local Contrastive Learning Framework for Cross-lingual Spoken Language UnderstandingLong42 citations
303. MMCoQA: Conversational Question Answering over Text, Tables, and ImagesLong42 citations
304. Measuring and Mitigating Name Biases in Neural Machine TranslationLong42 citations
305. Multilingual Molecular Representation Learning via Contrastive Pre-trainingLong42 citations
306. Neural Machine Translation with Phrase-Level Universal Visual RepresentationsLong42 citations
307. PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text GenerationLong42 citations
308. A Feasibility Study of Answer-Agnostic Question Generation for EducationFindings41 citations
309. Analyzing Dynamic Adversarial Training Data in the LimitFindings41 citations
310. Disentangled Sequence to Sequence Learning for Compositional GeneralizationLong41 citations
311. Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph ExpertsFindings41 citations
312. Efficient Cluster-Based k-Nearest-Neighbor Machine TranslationLong41 citations
313. End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video GroundingLong41 citations
314. Few-Shot Learning with Siamese Networks and Label TuningLong41 citations
315. Generating Scientific Definitions with Controllable ComplexityLong41 citations
316. GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue SystemsLong41 citations
317. Image Retrieval from Contextual DescriptionsLong41 citations
318. MReD: A Meta-Review Dataset for Structure-Controllable Text GenerationFindings41 citations
319. Training Text-to-Text Transformers with Privacy GuaranteesFindings41 citations
320. Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze?Long40 citations
321. MDCSpell: A Multi-task Detector-Corrector Framework for Chinese Spelling CorrectionFindings40 citations
322. Multi-Granularity Semantic Aware Graph Model for Reducing Position Bias in Emotion Cause Pair ExtractionFindings40 citations
323. On the Importance of Effectively Adapting Pretrained Language Models for Active LearningShort40 citations
324. Question Generation for Reading Comprehension Assessment by Modeling How and What to AskFindings40 citations
325. The Power of Prompt Tuning for Low-Resource Semantic ParsingShort40 citations
326. Towards Learning (Dis)-Similarity of Source Code from Program ContrastsLong40 citations
327. e-CARE: a New Dataset for Exploring Explainable Causal ReasoningLong40 citations
328. A Neural Pairwise Ranking Model for Readability AssessmentFindings39 citations
329. A Rationale-Centric Framework for Human-in-the-loop Machine LearningLong39 citations
330. A Statutory Article Retrieval Dataset in FrenchLong39 citations
331. CRASpell: A Contextual Typo Robust Approach to Improve Chinese Spelling CorrectionFindings39 citations
332. Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal ViewLong39 citations
333. FaiRR: Faithful and Robust Deductive Reasoning over Natural LanguageLong39 citations
334. Pre-training to Match for Unified Low-shot Relation ExtractionLong39 citations
335. Quantified Reproducibility Assessment of NLP ResultsLong39 citations
336. SalesBot: Transitioning from Chit-Chat to Task-Oriented DialoguesLong39 citations
337. Dynamic Global Memory for Document-level Argument ExtractionLong38 citations
338. Enhancing Cross-lingual Natural Language Inference by Prompt-learning from Cross-lingual TemplatesLong38 citations
339. Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory FeaturesLong38 citations
340. MTRec: Multi-Task Learning over BERT for News RecommendationFindings38 citations
341. Neural reality of argument structure constructionsLong38 citations
342. Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and DefenseFindings38 citations
343. Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research ManifoldFindings38 citations
344. Training Dynamics for Text Summarization ModelsFindings38 citations
345. AlephBERT: Language Model Pre-training and Evaluation from Sub-Word to Sentence LevelLong37 citations
346. ConditionalQA: A Complex Reading Comprehension Dataset with Conditional AnswersLong37 citations
347. DEAM: Dialogue Coherence Evaluation using AMR-based Semantic ManipulationsLong37 citations
348. Divide and Conquer: Text Semantic Matching with Disentangled Keywords and IntentsFindings37 citations
349. Hierarchical Sketch Induction for Paraphrase GenerationLong37 citations
350. Identifying Moments of Change from Longitudinal User TextLong37 citations
351. Improving Personalized Explanation Generation through VisualizationLong37 citations
352. Length Control in Abstractive Summarization by Pretraining Information SelectionLong37 citations
353. Pretraining with Artificial Language: Studying Transferable Knowledge in Language ModelsLong37 citations
354. Primum Non Nocere: Before working with Indigenous data, the ACL must confront ongoing colonialismShort37 citations
355. Prompt-Driven Neural Machine TranslationFindings37 citations
356. RoCBert: Robust Chinese Bert with Multimodal Contrastive PretrainingLong37 citations
357. SciNLI: A Corpus for Natural Language Inference on Scientific TextLong37 citations
358. The Moral Debater: A Study on the Computational Generation of Morally Framed ArgumentsLong37 citations
359. An Isotropy Analysis in the Multilingual BERT Embedding SpaceFindings36 citations
360. DiBiMT: A Novel Benchmark for Measuring Word Sense Disambiguation Biases in Machine TranslationLong36 citations
361. HeterMPC: A Heterogeneous Graph Neural Network for Response Generation in Multi-Party ConversationsLong36 citations
362. Improving Word Translation via Two-Stage Contrastive LearningLong36 citations
363. Interpretability for Language Learners Using Example-Based Grammatical Error CorrectionLong36 citations
364. Neural Pipeline for Zero-Shot Data-to-Text GenerationLong36 citations
365. Visual-Language Navigation Pretraining via Prompt-based Environmental Self-explorationLong36 citations
366. latent-GLAT: Glancing at Latent Variables for Parallel Text GenerationLong36 citations
367. Alignment-Augmented Consistent Translation for Multilingual Open Information ExtractionLong35 citations
368. Assessing Multilingual Fairness in Pre-trained Multimodal RepresentationsFindings35 citations
369. Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled LearningLong35 citations
370. E-KAR: A Benchmark for Rationalizing Natural Language Analogical ReasoningFindings35 citations
371. FORTAP: Using Formulas for Numerical-Reasoning-Aware Table PretrainingLong35 citations
372. FewNLU: Benchmarking State-of-the-Art Methods for Few-Shot Natural Language UnderstandingLong35 citations
373. Flooding-X: Improving BERT’s Resistance to Adversarial Attacks via Loss-Restricted Fine-TuningLong35 citations
374. Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial RobustnessFindings35 citations
375. HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic ParsingFindings35 citations
376. HLDC: Hindi Legal Documents CorpusFindings35 citations
377. How can NLP Help Revitalize Endangered Languages? A Case Study and Roadmap for the Cherokee LanguageLong35 citations
378. Knowledge Enhanced Reflection Generation for Counseling DialoguesLong35 citations
379. Learn and Review: Enhancing Continual Named Entity Recognition via Reviewing Synthetic SamplesFindings35 citations
380. Leveraging Similar Users for Personalized Language Modeling with Limited DataLong35 citations
381. On the Sensitivity and Stability of Model Interpretations in NLPLong35 citations
382. Rare Tokens Degenerate All Tokens: Improving Neural Text Generation via Adaptive Gradient Gating for Rare Token EmbeddingsLong35 citations
383. Redistributing Low-Frequency Words: Making the Most of Monolingual Data in Non-Autoregressive TranslationLong35 citations
384. Requirements and Motivations of Low-Resource Speech Synthesis for Language RevitalizationLong35 citations
385. Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table PerturbationLong35 citations
386. “That Is a Suspicious Reaction!”: Interpreting Logits Variation to Detect NLP Adversarial AttacksLong35 citations
387. A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional GenerationLong34 citations
388. AdapLeR: Speeding up Inference by Adaptive Length ReductionLong34 citations
389. CQG: A Simple and Effective Controlled Generation Framework for Multi-hop Question GenerationLong34 citations
390. Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocREDLong34 citations
391. FaVIQ: FAct Verification from Information-seeking QuestionsLong34 citations
392. Improving the Adversarial Robustness of NLP Models by Information BottleneckFindings34 citations
393. Nibbling at the Hard Core of Word Sense DisambiguationLong34 citations
394. Saliency as Evidence: Event Detection with Trigger Saliency AttributionLong34 citations
395. Spurious Correlations in Reference-Free Evaluation of Text GenerationLong34 citations
396. Universal Conditional Masked Language Pre-training for Neural Machine TranslationLong34 citations
397. Why don’t people use character-level machine translation?Findings34 citations
398. ConTinTin: Continual Learning from Task InstructionsLong33 citations
399. Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine TranslationLong33 citations
400. MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic PerspectiveLong33 citations
401. Modality-specific Learning Rates for Effective Multimodal Additive Late-fusionFindings33 citations
402. Not always about you: Prioritizing community needs when developing endangered language technologyLong33 citations
403. On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and SaliencyLong33 citations
404. Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation?Findings33 citations
405. Prompt Tuning for Discriminative Pre-trained Language ModelsFindings33 citations
406. QAConv: Question Answering on Informative ConversationsLong33 citations
407. Revisiting the Compositional Generalization Abilities of Neural Sequence ModelsShort33 citations
408. Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web DataLong33 citations
409. Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune ParadigmLong33 citations
410. Unsupervised Extractive Opinion Summarization Using Sparse CodingLong33 citations
411. When classifying grammatical role, BERT doesn’t care about word order... except when it mattersShort33 citations
412. Your Answer is Incorrect... Would you like to know why? Introducing a Bilingual Short Answer Feedback DatasetLong33 citations
413. Adapting Coreference Resolution Models through Active LearningLong32 citations
414. Clickbait Spoiling via Question Answering and Passage RetrievalLong32 citations
415. Distributed NLI: Learning to Predict Human Opinion Distributions for Language ReasoningFindings32 citations
416. Investigating Failures of Automatic Translationin the Case of Unambiguous GenderLong32 citations
417. Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech TranslationShort32 citations
418. When to Use Multi-Task Learning vs Intermediate Fine-Tuning for Pre-Trained Encoder Transfer LearningShort32 citations
419. AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading ComprehensionLong31 citations
420. CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text GenerationLong31 citations
421. Event-Event Relation Extraction using Probabilistic Box EmbeddingShort31 citations
422. Factual Consistency of Multilingual Pretrained Language ModelsFindings31 citations
423. ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence GenerationLong31 citations
424. SRL4E – Semantic Role Labeling for Emotions: A Unified Evaluation FrameworkLong31 citations
425. There Are a Thousand Hamlets in a Thousand People’s Eyes: Enhancing Knowledge-grounded Dialogue with Personal MemoryLong31 citations
426. Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue SystemsFindings31 citations
427. Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor AreasLong30 citations
428. CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractionsFindings30 citations
429. Canary Extraction in Natural Language Understanding ModelsShort30 citations
430. End-to-End Segmentation-based News SummarizationFindings30 citations
431. GPT-D: Inducing Dementia-related Linguistic Anomalies by Deliberate Degradation of Artificial Neural Language ModelsLong30 citations
432. Improving Event Representation via Simultaneous Weakly Supervised Contrastive Learning and ClusteringLong30 citations
433. Improving Relation Extraction through Syntax-induced Pre-training with Dependency MaskingFindings30 citations
434. IsoScore: Measuring the Uniformity of Embedding Space UtilizationFindings30 citations
435. Modeling Hierarchical Syntax Structure with Triplet Position for Source Code SummarizationLong30 citations
436. Mukayese: Turkish NLP Strikes BackFindings30 citations
437. Other Roles Matter! Enhancing Role-Oriented Dialogue Summarization via Role InteractionsLong30 citations
438. Probing for Predicate Argument Structures in Pretrained Language ModelsLong30 citations
439. ProtoTEx: Explaining Model Decisions with Prototype TensorsLong30 citations
440. Retrieval-guided Counterfactual Generation for QALong30 citations
441. Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product Attribute ExtractionShort30 citations
442. Towards Making the Most of Cross-Lingual Transfer for Zero-Shot Neural Machine TranslationLong30 citations
443. Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech TranslationLong30 citations
444. Cross-domain Named Entity Recognition via Graph MatchingFindings29 citations
445. EntSUM: A Data Set for Entity-Centric Extractive SummarizationLong29 citations
446. IAM: A Comprehensive and Large-Scale Dataset for Integrated Argument Mining TasksLong29 citations
447. Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise SettingFindings29 citations
448. Improving Meta-learning for Low-resource Text Classification and Generation via Memory ImitationLong29 citations
449. Just Rank: Rethinking Evaluation with Word and Sentence SimilaritiesLong29 citations
450. Learning to Imagine: Integrating Counterfactual Thinking in Neural Discrete ReasoningLong29 citations
451. NEWTS: A Corpus for News Topic-Focused SummarizationFindings29 citations
452. PriMock57: A Dataset Of Primary Care Mock ConsultationsShort29 citations
453. Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR ErrorsFindings29 citations
454. Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification TasksShort29 citations
455. UniTranSeR: A Unified Transformer Semantic Representation Framework for Multimodal Task-Oriented Dialog SystemLong29 citations
456. Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language GenerationFindings29 citations
457. DARER: Dual-task Temporal Relational Recurrent Reasoning Network for Joint Dialog Sentiment Classification and Act RecognitionFindings28 citations
458. End-to-End Speech Translation for Code Switched SpeechFindings28 citations
459. Guided Attention Multimodal Multitask Financial Forecasting with Inter-Company Relationships and Global and Local NewsLong28 citations
460. Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question AnsweringLong28 citations
461. Modeling Multi-hop Question Answering as Single Sequence PredictionLong28 citations
462. SCD: Self-Contrastive Decorrelation of Sentence EmbeddingsShort28 citations
463. Sense Embeddings are also Biased – Evaluating Social Biases in Static and Contextualised Sense EmbeddingsLong28 citations
464. The Trade-offs of Domain Adaptation for Neural Language ModelsLong28 citations
465. Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-DeploymentFindings28 citations
466. Virtual Augmentation Supported Contrastive Learning of Sentence RepresentationsFindings28 citations
467. Zero-Shot Cross-lingual Semantic ParsingLong28 citations
468. ASSIST: Towards Label Noise-Robust Dialogue State TrackingFindings27 citations
469. An Unsupervised Multiple-Task and Multiple-Teacher Model for Cross-lingual Named Entity RecognitionLong27 citations
470. Are Prompt-based Models Clueless?Long27 citations
471. BiTIIMT: A Bilingual Text-infilling Method for Interactive Machine TranslationLong27 citations
472. C3KG: A Chinese Commonsense Conversation Knowledge GraphFindings27 citations
473. Cluster & Tune: Boost Cold Start Performance in Text ClassificationLong27 citations
474. Continual Pre-training of Language Models for Math Problem Understanding with Syntax-Aware Memory NetworkLong27 citations
475. Improving Compositional Generalization with Self-Training for Data-to-Text GenerationLong27 citations
476. Learning Disentangled Semantic Representations for Zero-Shot Cross-Lingual Transfer in Multilingual Machine Reading ComprehensionLong27 citations
477. MetaWeighting: Learning to Weight Tasks in Multi-Task LearningFindings27 citations
478. Multimodal Sarcasm Target Identification in TweetsLong27 citations
479. PARE: A Simple and Strong Baseline for Monolingual and Multilingual Distantly Supervised Relation ExtractionShort27 citations
480. Probing as Quantifying Inductive BiasLong27 citations
481. Sentence-level Privacy for Document EmbeddingsLong27 citations
482. Slangvolution: A Causal Analysis of Semantic Change and Frequency Dynamics in SlangLong27 citations
483. An Effective and Efficient Entity Alignment Decoding Algorithm via Third-Order Tensor IsomorphismLong26 citations
484. An Imitation Learning Curriculum for Text Editing with Non-Autoregressive ModelsLong26 citations
485. Can a Transformer Pass the Wug Test? Tuning Copying Bias in Neural Morphological Inflection ModelsShort26 citations
486. Few-shot Controllable Style Transfer for Low-Resource Multilingual SettingsLong26 citations
487. First the Worst: Finding Better Gender Translations During Beam SearchFindings26 citations
488. How does the pre-training objective affect what large language models learn about linguistic properties?Short26 citations
489. HybriDialogue: An Information-Seeking Dialogue Dataset Grounded on Tabular and Textual DataFindings26 citations
490. Learning When to Translate for Streaming SpeechLong26 citations
491. On Continual Model Refinement in Out-of-Distribution Data StreamsLong26 citations
492. Prior Knowledge and Memory Enriched Transformer for Sign Language TranslationFindings26 citations
493. RST Discourse Parsing with Second-Stage EDU-Level Pre-trainingLong26 citations
494. Sentence-aware Contrastive Learning for Open-Domain Passage RetrievalLong26 citations
495. SkipBERT: Efficient Inference with Shallow Layer SkippingLong26 citations
496. Towards Collaborative Neural-Symbolic Graph Semantic Parsing via UncertaintyFindings26 citations
497. Two Birds with One Stone: Unified Model Learning for Both Recall and Ranking in News RecommendationFindings26 citations
498. UNIMO-2: End-to-End Unified Vision-Language Grounded LearningFindings26 citations
499. What to Learn, and How: Toward Effective Learning from RationalesFindings26 citations
500. AMR-DA: Data Augmentation by Abstract Meaning RepresentationFindings25 citations
501. BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic LanguagesFindings25 citations
502. Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine TranslationLong25 citations
503. Can Explanations Be Useful for Calibrating Black Box Models?Long25 citations
504. CipherDAug: Ciphertext based Data Augmentation for Neural Machine TranslationLong25 citations
505. Comparative Opinion Summarization via Collaborative DecodingFindings25 citations
506. DEEP: DEnoising Entity Pre-training for Neural Machine TranslationLong25 citations
507. Fully-Semantic Parsing and Generation: the BabelNet Meaning RepresentationLong25 citations
508. GCPG: A General Framework for Controllable Paraphrase GenerationFindings25 citations
509. Impact of Evaluation Methodologies on Code SummarizationLong25 citations
510. Improving Generalizability in Implicitly Abusive Language Detection with Concept Activation VectorsLong25 citations
511. Improving Zero-Shot Cross-lingual Transfer Between Closely Related Languages by Injecting Character-Level NoiseFindings25 citations
512. Learning Confidence for Transformer-based Neural Machine TranslationLong25 citations
513. Learning Non-Autoregressive Models from Search for Unsupervised Sentence SummarizationLong25 citations
514. LexSubCon: Integrating Knowledge from Lexical Resources into Contextual Embeddings for Lexical SubstitutionLong25 citations
515. Modeling Persuasive Discourse to Adaptively Support Students’ Argumentative WritingLong25 citations
516. Morphosyntactic Tagging with Pre-trained Language Models for Arabic and its DialectsFindings25 citations
517. On the probability–quality paradox in language generationShort25 citations
518. Question Answering Infused Pre-training of General-Purpose Contextualized RepresentationsFindings25 citations
519. Robust Lottery Tickets for Pre-trained Language ModelsLong25 citations
520. Structural Characterization for Dialogue DisentanglementLong25 citations
521. The impact of lexical and grammatical processing on generating code from natural languageFindings25 citations
522. Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence LearningLong25 citations
523. Using Context-to-Vector with Graph Retrofitting to Improve Word EmbeddingsLong25 citations
524. Zero-shot Learning for Grapheme to Phoneme Conversion with Language EnsembleFindings25 citations
525. A Taxonomy of Empathetic Questions in Social DialogsLong24 citations
526. As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive ConditioningShort24 citations
527. Contextual Representation Learning beyond Masked Language ModelingLong24 citations
528. Dataset Geography: Mapping Language Data to Language UsersLong24 citations
529. Decoding Part-of-Speech from Human EEG SignalsLong24 citations
530. Imputing Out-of-Vocabulary Embeddings with LOVE Makes LanguageModels Robust with Little CostLong24 citations
531. SHIELD: Defending Textual Neural Networks against Multiple Black-Box Adversarial Attacks with Stochastic Multi-Expert PatcherLong24 citations
532. Semantically Distributed Robust Optimization for Vision-and-Language InferenceFindings24 citations
533. The patient is more dead than alive: exploring the current state of the multi-document summarisation of the biomedical literatureLong24 citations
534. Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment AnalysisFindings24 citations
535. Type-Driven Multi-Turn Corrections for Grammatical Error CorrectionFindings24 citations
536. Beyond the Granularity: Multi-Perspective Dialogue Collaborative Selection for Dialogue State TrackingLong23 citations
537. Can Unsupervised Knowledge Transfer from Social Discussions Help Argument Mining?Long23 citations
538. Context Matters: A Pragmatic Study of PLMs’ Negation UnderstandingLong23 citations
539. Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive LearningShort23 citations
540. Ditch the Gold Standard: Re-evaluating Conversational Question AnsweringLong23 citations
541. Good Night at 4 pm?! Time Expressions in Different CulturesFindings23 citations
542. Listening to Affected Communities to Define Extreme Speech: Dataset and ExperimentsFindings23 citations
543. MSCTD: A Multimodal Sentiment Chat Translation DatasetLong23 citations
544. Modeling Dual Read/Write Paths for Simultaneous Machine TranslationLong23 citations
545. Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related LanguagesLong23 citations
546. Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional ManualsLong23 citations
547. “Is Whole Word Masking Always Better for Chinese BERT?”: Probing on Chinese Grammatical Error CorrectionFindings23 citations
548. (Un)solving Morphological Inflection: Lemma Overlap Artificially Inflates Models’ PerformanceShort22 citations
549. AbductionRules: Training Transformers to Explain Unexpected InputsFindings22 citations
550. Attention Temperature Matters in Abstractive Summarization DistillationLong22 citations
551. Co-VQA : Answering by Interactive Sub Question SequenceFindings22 citations
552. From the Detection of Toxic Spans in Online Discussions to the Analysis of Toxic-to-Civil TransferLong22 citations
553. How Do Seq2Seq Models Perform on End-to-End Data-to-Text Generation?Long22 citations
554. Human Language ModelingFindings22 citations
555. Learn to Adapt for Generalized Zero-Shot Text ClassificationLong22 citations
556. Multi Task Learning For Zero Shot Performance Prediction of Multilingual ModelsLong22 citations
557. Multitasking Framework for Unsupervised Simple Definition GenerationLong22 citations
558. Perceiving the World: Question-guided Reinforcement Learning for Text-based GamesLong22 citations
559. Plug-and-Play Adaptation for Continuously-updated QAFindings22 citations
560. Word2Box: Capturing Set-Theoretic Semantics of Words using Box EmbeddingsLong22 citations
561. A Multi-Document Coverage Reward for RELAXed Multi-Document SummarizationLong21 citations
562. A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence EmbeddingsFindings21 citations
563. ABC: Attention with Bounded-memory ControlLong21 citations
564. An Empirical Study on Explanations in Out-of-Domain SettingsLong21 citations
565. Answer Uncertainty and Unanswerability in Multiple-Choice Machine Reading ComprehensionFindings21 citations
566. Automated Crossword SolvingLong21 citations
567. Automatic Identification and Classification of Bragging in Social MediaLong21 citations
568. CogTaskonomy: Cognitively Inspired Task Taxonomy Is Beneficial to Transfer Learning in NLPLong21 citations
569. DS-TOD: Efficient Domain Specialization for Task-Oriented DialogFindings21 citations
570. Dependency Parsing as MRC-based Span-Span PredictionLong21 citations
571. Does BERT really agree ? Fine-grained Analysis of Lexical Dependence on a Syntactic TaskFindings21 citations
572. FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metrics for Automatic Text GenerationLong21 citations
573. Interpreting the Robustness of Neural NLP Models to Textual PerturbationsFindings21 citations
574. Learned Incremental Representations for ParsingLong21 citations
575. Learning Disentangled Representations of Negation and UncertaintyLong21 citations
576. Leveraging Knowledge in Multilingual Commonsense ReasoningFindings21 citations
577. Logic Traps in Evaluating Attribution ScoresLong21 citations
578. Open Vocabulary Extreme Classification Using Generative ModelsFindings21 citations
579. Pyramid-BERT: Reducing Complexity via Successive Core-set based Token SelectionLong21 citations
580. Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word DistributionsLong21 citations
581. WatClaimCheck: A new Dataset for Claim Entailment and InferenceLong21 citations
582. What is wrong with you?: Leveraging User Sentiment for Automatic Dialog EvaluationFindings21 citations
583. WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity TypesLong21 citations
584. A Risk-Averse Mechanism for Suicidality Assessment on Social MediaShort20 citations
585. Divide and Rule: Effective Pre-Training for Context-Aware Multi-Encoder Translation ModelsLong20 citations
586. Do self-supervised speech models develop human-like perception biases?Long20 citations
587. Fair and Argumentative Language Modeling for Computational ArgumentationLong20 citations
588. Few-Shot Tabular Data Enrichment Using Fine-Tuned Transformer ArchitecturesLong20 citations
589. ILDAE: Instance-Level Difficulty Analysis of Evaluation DataLong20 citations
590. Improving Candidate Retrieval with Entity Profile Generation for Wikidata Entity LinkingFindings20 citations
591. Inverse is Better! Fast and Accurate Prompt for Few-shot Slot TaggingFindings20 citations
592. Learning Adaptive Segmentation Policy for End-to-End Simultaneous TranslationLong20 citations
593. Local Structure Matters Most: Perturbation Study in NLUFindings20 citations
594. MIMICause: Representation and automatic extraction of causal relation types from clinical notesFindings20 citations
595. On the Importance of Data Size in Probing Fine-tuned ModelsFindings20 citations
596. Predicting Difficulty and Discrimination of Natural Language QuestionsShort20 citations
597. Richer Countries and Richer RepresentationsFindings20 citations
598. Sequence-to-sequence AMR Parsing with Ancestor InformationShort20 citations
599. A Novel Framework Based on Medical Concept Driven Attention for Explainable Medical Code Prediction via External KnowledgeFindings19 citations
600. Adjusting the Precision-Recall Trade-Off with Align-and-Predict Decoding for Grammatical Error CorrectionShort19 citations
601. An Accurate Unsupervised Method for Joint Entity Alignment and Dangling Entity DetectionFindings19 citations
602. An Empirical Study of Memorization in NLPLong19 citations
603. Answer-level Calibration for Free-form Multiple Choice Question AnsweringLong19 citations
604. Bias Mitigation in Machine Translation Quality EstimationLong19 citations
605. CoCoLM: Complex Commonsense Enhanced Language Model with Discourse RelationsFindings19 citations
606. Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine TranslationLong19 citations
607. DiS-ReX: A Multilingual Dataset for Distantly Supervised Relation ExtractionShort19 citations
608. Gaussian Multi-head Attention for Simultaneous Machine TranslationFindings19 citations
609. Graph Refinement for Coreference ResolutionFindings19 citations
610. Have my arguments been replied to? Argument Pair Extraction as Machine Reading ComprehensionShort19 citations
611. Hierarchical Curriculum Learning for AMR ParsingShort19 citations
612. Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual TransferabilityLong19 citations
613. OCR Improves Machine Translation for Low-Resource LanguagesFindings19 citations
614. One Agent To Rule Them All: Towards Multi-agent Conversational AIFindings19 citations
615. Predicate-Argument Based Bi-Encoder for Paraphrase IdentificationLong19 citations
616. Probing Simile Knowledge from Pre-trained Language ModelsLong19 citations
617. Rethinking Negative Sampling for Handling Missing Entity AnnotationsLong19 citations
618. Rethinking and Refining the Distinct MetricShort19 citations
619. A Natural Diet: Towards Improving Naturalness of Machine Translation OutputFindings18 citations
620. Accelerating Code Search with Deep Hashing and Code ClassificationLong18 citations
621. Attention as Grounding: Exploring Textual and Cross-Modal Attention on Entities and Relations in Language-and-Vision TransformerFindings18 citations
622. Better Language Model with Hypernym Class PredictionLong18 citations
623. ClusterFormer: Neural Clustering Attention for Efficient and Effective TransformerLong18 citations
624. Comprehensive Multi-Modal Interactions for Referring Image SegmentationFindings18 citations
625. Controllable Dictionary Example Generation: Generating Example Sentences for Specific Targeted AudiencesLong18 citations
626. Deep Inductive Logic Reasoning for Multi-Hop Reading ComprehensionLong18 citations
627. Deep Reinforcement Learning for Entity AlignmentFindings18 citations
628. Efficient Unsupervised Sentence Compression by Fine-tuning Transformers with Reinforcement LearningLong18 citations
629. Encoding and Fusing Semantic Connection and Linguistic Evidence for Implicit Discourse Relation RecognitionFindings18 citations
630. Learning Bias-reduced Word Embeddings Using Dictionary DefinitionsFindings18 citations
631. Learning to Robustly Aggregate Labeling Functions for Semi-supervised Data ProgrammingFindings18 citations
632. Read Top News First: A Document Reordering Approach for Multi-Document News SummarizationFindings18 citations
633. Reducing Position Bias in Simultaneous Machine Translation with Length-Aware FrameworkLong18 citations
634. Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language ModelsLong18 citations
635. Table-based Fact Verification with Self-adaptive Mixture of ExpertsFindings18 citations
636. The Change that Matters in Discourse Parsing: Estimating the Impact of Domain Shift on Parser ErrorFindings18 citations
637. To be or not to be an Integer? Encoding Variables for Mathematical TextFindings18 citations
638. Toward Annotator Group Bias in CrowdsourcingLong18 citations
639. What does it take to bake a cake? The RecipeRef corpus and anaphora resolution in procedural textFindings18 citations
640. A Graph Enhanced BERT Model for Event PredictionFindings17 citations
641. BenchIE: A Framework for Multi-Faceted Fact-Based Open Information Extraction EvaluationLong17 citations
642. Breaking Down Multilingual Machine TranslationFindings17 citations
643. Bridging the Generalization Gap in Text-to-SQL Parsing with Schema ExpansionLong17 citations
644. CARETS: A Consistency And Robustness Evaluative Test Suite for VQALong17 citations
645. Challenges to Open-Domain Constituency ParsingFindings17 citations
646. Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine TranslationLong17 citations
647. Document-Level Event Argument Extraction via Optimal TransportFindings17 citations
648. DuReadervis: A Chinese Dataset for Open-domain Document Visual Question AnsweringFindings17 citations
649. Entailment Graph Learning with Textual Entailment and Soft TransitivityLong17 citations
650. FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation FrameworkLong17 citations
651. How Do We Answer Complex Questions: Discourse Structure of Long-form AnswersLong17 citations
652. Lacking the Embedding of a Word? Look it up into a Traditional DictionaryFindings17 citations
653. Learning the Beauty in Songs: Neural Singing Voice BeautifierLong17 citations
654. MILIE: Modular & Iterative Multilingual Open Information ExtractionLong17 citations
655. Meta-Learning for Fast Cross-Lingual Adaptation in Dependency ParsingLong17 citations
656. Multi-Party Empathetic Dialogue Generation: A New Task for Dialog SystemsLong17 citations
657. Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine TranslationLong17 citations
658. Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style TransferShort17 citations
659. Multimodal fusion via cortical network inspired lossesLong17 citations
660. QuoteR: A Benchmark of Quote Recommendation for WritingLong17 citations
661. Synthetic Question Value Estimation for Domain Adaptation of Question AnsweringLong17 citations
662. Towards Better Characterization of ParaphrasesLong17 citations
663. Translate-Train Embracing Translationese ArtifactsShort17 citations
664. Unsupervised Natural Language Inference Using PHL Triplet GenerationFindings17 citations
665. WLASL-LEX: a Dataset for Recognising Phonological Properties in American Sign LanguageShort17 citations
666. [CASPI] Causal-aware Safe Policy Improvement for Task-oriented DialogueLong17 citations
667. Automatic Song Translation for Tonal LanguagesFindings16 citations
668. Buy Tesla, Sell Ford: Assessing Implicit Stock Market Preference in Pre-trained Language ModelsShort16 citations
669. Cross-Lingual Contrastive Learning for Fine-Grained Entity Typing for Low-Resource LanguagesLong16 citations
670. CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language UnderstandingFindings16 citations
671. Does BERT Know that the IS-A Relation Is Transitive?Short16 citations
672. GRS: Combining Generation and Revision in Unsupervised Sentence SimplificationFindings16 citations
673. How reparametrization trick broke differentially-private text representation learningShort16 citations
674. Modeling Intensification for Sign Language Generation: A Computational ApproachFindings16 citations
675. Morphological Processing of Low-Resource Languages: Where We Are and What’s NextFindings16 citations
676. Non-neural Models Matter: a Re-evaluation of Neural Referring Expression Generation SystemsLong16 citations
677. Probing BERT’s priors with serial reproduction chainsFindings16 citations
678. Rethinking Self-Supervision Objectives for Generalizable Coherence ModelingLong16 citations
679. Semi-Supervised Formality Style Transfer with Consistency TrainingLong16 citations
680. Toward More Meaningful Resources for Lower-resourced LanguagesFindings16 citations
681. Translation Error Detection as Rationale ExtractionFindings16 citations
682. Unsupervised multiple-choice question generation for out-of-domain Q&A fine-tuningShort16 citations
683. VISITRON: Visual Semantics-Aligned Interactively Trained Object-NavigatorFindings16 citations
684. What Makes Reading Comprehension Questions Difficult?Long16 citations
685. Can Pre-trained Language Models Interpret Similes as Smart as Human?Long15 citations
686. Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain ConversationsLong15 citations
687. Differentiable Multi-Agent Actor-Critic for Multi-Step Radiology Report SummarizationLong15 citations
688. ED2LM: Encoder-Decoder to Language Model for Faster Document Re-ranking InferenceFindings15 citations
689. Efficient Argument Structure Extraction with Transfer Learning and Active LearningFindings15 citations
690. Efficient, Uncertainty-based Moderation of Neural Networks Text ClassifiersFindings15 citations
691. Generative Pretraining for Paraphrase EvaluationLong15 citations
692. Hey AI, Can You Solve Complex Tasks by Talking to Agents?Findings15 citations
693. Improving Controllable Text Generation with Position-Aware Weighted DecodingFindings15 citations
694. Integrating Vectorized Lexical Constraints for Neural Machine TranslationLong15 citations
695. Large Scale Substitution-based Word Sense InductionLong15 citations
696. Learning and Evaluating Character Representations in NovelsFindings15 citations
697. Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to DocumentsLong15 citations
698. Prediction Difference Regularization against Perturbation for Neural Machine TranslationLong15 citations
699. Prix-LM: Pretraining for Multilingual Knowledge Base ConstructionLong15 citations
700. RELiC: Retrieving Evidence for Literary ClaimsLong15 citations
701. Situated Dialogue Learning through Procedural Environment GenerationLong15 citations
702. Towards Few-shot Entity Recognition in Document Images: A Label-aware Sequence-to-Sequence FrameworkFindings15 citations
703. Towards Responsible Natural Language Annotation for the Varieties of ArabicFindings15 citations
704. Towards Transparent Interactive Semantic Parsing via Step-by-Step CorrectionFindings15 citations
705. Where to Go for the Holidays: Towards Mixed-Type Dialogs for Clarification of User GoalsLong15 citations
706. A Simple but Effective Pluggable Entity Lookup Table for Pre-trained Language ModelsShort14 citations
707. An Interpretable Neuro-Symbolic Reasoning Framework for Task-Oriented Dialogue GenerationLong14 citations
708. Analyzing Wrap-Up Effects through an Information-Theoretic LensShort14 citations
709. Automatic Error Analysis for Document-level Information ExtractionLong14 citations
710. Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language RepresentationsLong14 citations
711. Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text GenerationLong14 citations
712. Measuring the Impact of (Psycho-)Linguistic and Readability Features and Their Spill Over Effects on the Prediction of Eye Movement PatternsLong14 citations
713. On The Ingredients of an Effective Zero-shot Semantic ParserLong14 citations
714. Open Relation Modeling: Learning to Define Relations between EntitiesFindings14 citations
715. ProphetChat: Enhancing Dialogue Generation with Simulation of Future ConversationLong14 citations
716. Rare and Zero-shot Word Sense Disambiguation using Z-ReweightingLong14 citations
717. Reports of personal experiences and stories in argumentation: datasets and analysisLong14 citations
718. Scheduled Multi-task Learning for Neural Chat TranslationLong14 citations
719. Updated Headline Generation: Creating Updated Summaries for Evolving News StoriesLong14 citations
720. What does the sea say to the shore? A BERT based DST style approach for speaker to dialogue attribution in novelsLong14 citations
721. A Meta-framework for Spatiotemporal Quantity Extraction from TextLong13 citations
722. A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-SlotsFindings13 citations
723. Alternative Input Signals Ease Transfer in Multilingual Machine TranslationLong13 citations
724. Answering Open-Domain Multi-Answer Questions via a Recall-then-Verify FrameworkLong13 citations
725. Automatic Speech Recognition and Query By Example for Creole Languages DocumentationFindings13 citations
726. Cross-Lingual Ability of Multilingual Masked Language Models: A Study of Language StructureLong13 citations
727. Cross-Modal Cloze Task: A New Task to Brain-to-Word DecodingFindings13 citations
728. Detecting Various Types of Noise for Neural Machine TranslationFindings13 citations
729. Efficient Hyper-parameter Search for Knowledge Graph EmbeddingLong13 citations
730. Exploring and Adapting Chinese GPT to Pinyin Input MethodLong13 citations
731. Identifying Chinese Opinion Expressions with Extremely-Noisy Crowdsourcing AnnotationsLong13 citations
732. Incorporating Stock Market Signals for Twitter Stance DetectionLong13 citations
733. Learning From Failure: Data Capture in an Australian Aboriginal CommunityLong13 citations
734. Learning to Mediate Disparities Towards Pragmatic CommunicationLong13 citations
735. On the Robustness of Offensive Language ClassifiersLong13 citations
736. Reinforcement Guided Multi-Task Learning Framework for Low-Resource Stereotype DetectionLong13 citations
737. Right for the Right Reason: Evidence Extraction for Trustworthy Tabular ReasoningLong13 citations
738. RoMe: A Robust Metric for Evaluating Natural Language GenerationLong13 citations
739. Should We Trust This Summary? Bayesian Abstractive Summarization to The RescueFindings13 citations
740. Simulating Bandit Learning from User Feedback for Extractive Question AnsweringLong13 citations
741. There’s a Time and Place for Reasoning Beyond the ImageLong13 citations
742. Towards Consistent Document-level Entity Linking: Joint Models for Entity Linking and Coreference ResolutionShort13 citations
743. UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded DialogueShort13 citations
744. Voxel-informed Language GroundingShort13 citations
745. When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data AugmentationFindings13 citations
746. “You might think about slightly revising the title”: Identifying Hedges in Peer-tutoring InteractionsLong13 citations
747. A Comparison of Strategies for Source-Free Domain AdaptationLong12 citations
748. A Novel Perspective to Look At Attention: Bi-level Attention-based Explainable Topic Modeling for News ClassificationFindings12 citations
749. Are Shortest Rationales the Best Explanations for Human Understanding?Short12 citations
750. ChatMatch: Evaluating Chatbots by Autonomous Chat TournamentsLong12 citations
751. Constructing Open Cloze Tests Using Generation and Discrimination Capabilities of TransformersFindings12 citations
752. Controlled Text Generation Using Dictionary Prior in Variational AutoencodersFindings12 citations
753. Cree Corpus: A Collection of nêhiyawêwin ResourcesLong12 citations
754. Divide and Denoise: Learning from Noisy Labels in Fine-Grained Entity Typing with Cluster-Wise Loss CorrectionLong12 citations
755. Doctor Recommendation in Online Health Forums via Expertise LearningLong12 citations
756. Domain Generalisation of NMT: Fusing Adapters with Leave-One-Domain-Out TrainingFindings12 citations
757. Extract-Select: A Span Selection Framework for Nested Named Entity Recognition with Generative Adversarial TrainingFindings12 citations
758. Improving Chinese Grammatical Error Detection via Data augmentation by Conditional Error GenerationFindings12 citations
759. Improving Machine Reading Comprehension with Contextualized Commonsense KnowledgeLong12 citations
760. Improving Robustness of Language Models from a Geometry-aware PerspectiveFindings12 citations
761. Metadata Shaping: A Simple Approach for Knowledge-Enhanced Language ModelsFindings12 citations
762. Probing for Labeled Dependency TreesLong12 citations
763. S4-Tuning: A Simple Cross-lingual Sub-network Tuning MethodShort12 citations
764. SDR: Efficient Neural Re-ranking using Succinct Document RepresentationLong12 citations
765. Syntax-guided Contrastive Learning for Pre-trained Language ModelFindings12 citations
766. TegTok: Augmenting Text Generation via Task-specific and Open-world KnowledgeFindings12 citations
767. Towards Abstractive Grounded Summarization of Podcast TranscriptsLong12 citations
768. Towards Comprehensive Patent Approval Predictions:Beyond Traditional Document ClassificationLong12 citations
769. Bilingual alignment transfers to multilingual alignment for unsupervised parallel text miningLong11 citations
770. CLUES: A Benchmark for Learning Classifiers using Natural Language ExplanationsLong11 citations
771. Distributionally Robust Finetuning BERT for Covariate Drift in Spoken Language UnderstandingLong11 citations
772. E-LANG: Energy-Based Joint Inferencing of Super and Swift Language ModelsLong11 citations
773. EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbersLong11 citations
774. Enhancing Chinese Pre-trained Language Model via Heterogeneous Linguistics GraphLong11 citations
775. Entity-based Neural Local Coherence ModelingLong11 citations
776. Event Transition Planning for Open-ended Text GenerationFindings11 citations
777. Finding the Dominant Winning Ticket in Pre-Trained Language ModelsFindings11 citations
778. From Simultaneous to Streaming Machine Translation by Leveraging Streaming HistoryLong11 citations
779. Headed-Span-Based Projective Dependency ParsingLong11 citations
780. Improving Multi-label Malevolence Detection in Dialogues through Multi-faceted Label Correlation EnhancementLong11 citations
781. Incremental Intent Detection for Medical Domain with Contrast Replay NetworksFindings11 citations
782. Learning to Describe Solutions for Bug Reports Based on Developer DiscussionsFindings11 citations
783. Learning to Generate Programs for Table Fact Verification via Structure-Aware Semantic ParsingLong11 citations
784. Leveraging Visual Knowledge in Language Tasks: An Empirical Study on Intermediate Pre-training for Cross-Modal Knowledge TransferLong11 citations
785. Measuring Fairness of Text Classifiers via Prediction SensitivityLong11 citations
786. Measuring the Language of Self-Disclosure across CorporaFindings11 citations
787. Multilingual Detection of Personal Employment Status on TwitterLong11 citations
788. OIE@OIA: an Adaptable and Efficient Open Information Extraction FrameworkLong11 citations
789. Pre-training and Fine-tuning Neural Topic Model: A Simple yet Effective Approach to Incorporating External KnowledgeLong11 citations
790. Predicting Sentence Deletions for Text Simplification Using a Functional Discourse StructureShort11 citations
791. Probing the Robustness of Trained Metrics for Conversational Dialogue SystemsShort11 citations
792. Striking a Balance: Alleviating Inconsistency in Pre-trained Models for Symmetric Classification TasksFindings11 citations
793. Substructure Distribution Projection for Zero-Shot Cross-Lingual Dependency ParsingLong11 citations
794. TABi: Type-Aware Bi-Encoders for Open-Domain Entity RetrievalFindings11 citations
795. Textomics: A Dataset for Genomics Data Summary GenerationLong11 citations
796. Towards Fair Evaluation of Dialogue State Tracking by Flexible Incorporation of Turn-level PerformancesShort11 citations
797. ePiC: Employing Proverbs in Context as a Benchmark for Abstract Language UnderstandingLong11 citations
798. A Few-Shot Semantic Parser for Wizard-of-Oz Dialogues with the Precise ThingTalk RepresentationFindings10 citations
799. A Neural Network Architecture for Program Understanding Inspired by Human BehaviorsLong10 citations
800. Augmenting Document Representations for Dense Retrieval with Interpolation and PerturbationShort10 citations
801. Capture Human Disagreement Distributions by Calibrated Networks for Natural Language InferenceFindings10 citations
802. Characterizing Idioms: Conventionality and ContingencyLong10 citations
803. Classification without (Proper) Representation: Political Heterogeneity in Social Media and Its Implications for Classification and Behavioral AnalysisFindings10 citations
804. Combining Static and Contextualised Multilingual EmbeddingsFindings10 citations
805. Compact Token Representations with Contextual Quantization for Efficient Document Re-rankingLong10 citations
806. Computational Historical Linguistics and Language Diversity in South AsiaLong10 citations
807. DMix: Adaptive Distance-aware Interpolative MixupShort10 citations
808. Direct parsing to sentiment graphsShort10 citations
809. Domain Knowledge Transferring for Pre-trained Language Model via Calibrated Activation Boundary DistillationLong10 citations
810. Estimating the Entropy of Linguistic DistributionsShort10 citations
811. Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive LearningLong10 citations
812. Finding Structural Knowledge in Multimodal-BERTLong10 citations
813. Fire Burns, Sword Cuts: Commonsense Inductive Bias for Exploration in Text-based GamesShort10 citations
814. Improving Neural Political Statement Classification with Class Hierarchical InformationFindings10 citations
815. Investigating Non-local Features for Neural Constituency ParsingLong10 citations
816. KenMeSH: Knowledge-enhanced End-to-end Biomedical Text LabellingLong10 citations
817. Learning from Sibling Mentions with Scalable Graph Inference in Fine-Grained Entity TypingLong10 citations
818. Learning to Rank Visual Stories From Human Ranking DataLong10 citations
819. Leveraging Wikipedia article evolution for promotional tone detectionLong10 citations
820. Mismatch between Multi-turn Dialogue and its Evaluation Metric in Dialogue State TrackingShort10 citations
821. Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual CluesLong10 citations
822. Principled Paraphrase Generation with Parallel CorporaLong10 citations
823. RNSum: A Large-Scale Dataset for Automatic Release Note Generation via Commit Logs SummarizationLong10 citations
824. Should a Chatbot be Sarcastic? Understanding User Preferences Towards Sarcasm GenerationLong10 citations
825. Sparsifying Transformer Models with Trainable Representation PoolingLong10 citations
826. Structural Supervision for Word Alignment and Machine TranslationFindings10 citations
827. Towards Adversarially Robust Text Classifiers by Learning to Reweight Clean ExamplesFindings10 citations
828. Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence ModelsLong10 citations
829. Understanding Game-Playing Agents with Natural Language AnnotationsShort10 citations
830. Understanding Gender Bias in Knowledge Base EmbeddingsLong10 citations
831. Automatic Detection of Entity-Manipulated Text using Factual KnowledgeShort9 citations
832. Calibration of Machine Reading Systems at ScaleFindings9 citations
833. Compressing Sentence Representation for Semantic Retrieval via Homomorphic Projective DistillationFindings9 citations
834. Explaining Classes through Stable Word AttributionsFindings9 citations
835. KaFSP: Knowledge-Aware Fuzzy Semantic Parsing for Conversational Question Answering over a Large-Scale Knowledge BaseLong9 citations
836. LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic ParsingLong9 citations
837. Learning Reasoning Patterns for Relational Triple Extraction with Mutual Generation of Text and GraphFindings9 citations
838. Mitigating Contradictions in Dialogue Based on Contrastive LearningFindings9 citations
839. Morphological Reinflection with Multiple Arguments: An Extended Annotation schema and a Georgian Case StudyShort9 citations
840. N-Shot Learning for Augmenting Task-Oriented Dialogue State TrackingFindings9 citations
841. On Efficiently Acquiring Annotations for Multilingual ModelsShort9 citations
842. On the Effect of Isotropy on VAE Representations of TextShort9 citations
843. Online Semantic Parsing for Latency Reduction in Task-Oriented DialogueLong9 citations
844. Probing Factually Grounded Content Transfer with Factual AblationFindings9 citations
845. Relevant CommonSense Subgraphs for “What if...” Procedural ReasoningFindings9 citations
846. Sememe Prediction for BabelNet Synsets using Multilingual and Multimodal InformationFindings9 citations
847. Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-SwitchingLong9 citations
848. Systematicity, Compositionality and Transitivity of Deep NLP Models: a Metamorphic Testing PerspectiveFindings9 citations
849. Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum LearningShort9 citations
850. A Transformational Biencoder with In-Domain Negative Sampling for Zero-Shot Entity LinkingFindings8 citations
851. Active Evaluation: Efficient NLG Evaluation with Few Pairwise ComparisonsLong8 citations
852. Better Quality Estimation for Low Resource Corpus MiningFindings8 citations
853. Compositional Generalization in Dependency ParsingLong8 citations
854. Constrained Multi-Task Learning for Bridging ResolutionLong8 citations
855. Counterfactual Explanations for Natural Language InterfacesShort8 citations
856. Cross-lingual Inference with A Chinese Entailment GraphFindings8 citations
857. Discontinuous Constituency and BERT: A Case Study of DutchFindings8 citations
858. Dynamically Refined Regularization for Improving Cross-corpora Hate Speech DetectionFindings8 citations
859. ECO v1: Towards Event-Centric Opinion MiningFindings8 citations
860. Early Stopping Based on Unlabeled Samples in Text ClassificationLong8 citations
861. Enhancing Natural Language Representation with Large-Scale Out-of-Domain CommonsenseFindings8 citations
862. Extracting Person Names from User Generated Text: Named-Entity Recognition for Combating Human TraffickingFindings8 citations
863. Fact-Tree Reasoning for N-ary Question Answering over Knowledge GraphsFindings8 citations
864. Flow-Adapter Architecture for Unsupervised Machine TranslationLong8 citations
865. Graph Neural Networks for Multiparallel Word AlignmentFindings8 citations
866. Learning from Missing Relations: Contrastive Learning with Commonsense Knowledge Graphs for Commonsense InferenceFindings8 citations
867. Leveraging Expert Guided Adversarial Augmentation For Improving Generalization in Named Entity RecognitionFindings8 citations
868. Life after BERT: What do Other Muppets Understand about Language?Long8 citations
869. Long-range Sequence Modeling with Predictable Sparse AttentionLong8 citations
870. Low-Rank Softmax Can Have Unargmaxable Classes in Theory but Rarely in PracticeLong8 citations
871. Machine Translation for Livonian: Catering to 20 SpeakersShort8 citations
872. Meta-XNLG: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and GenerationFindings8 citations
873. Multi-task Learning for Paraphrase Generation With Keyword and Part-of-Speech ReconstructionFindings8 citations
874. Selecting Stickers in Open-Domain Dialogue through Multitask LearningFindings8 citations
875. SyMCoM - Syntactic Measure of Code Mixing A Study Of English-Hindi Code-MixingFindings8 citations
876. Tracing Origins: Coreference-aware Machine Reading ComprehensionLong8 citations
877. Unsupervised Dependency Graph NetworkLong8 citations
878. Variational Graph Autoencoding as Cheap Supervision for AMR Coreference ResolutionLong8 citations
879. ZiNet: Linking Chinese Characters Spanning Three Thousand YearsFindings8 citations
880. k-Rater Reliability: The Correct Unit of Reliability for Aggregated Human AnnotationsShort8 citations
881. Benchmarking Answer Verification Methods for Question Answering-Based Summarization Evaluation MetricsFindings7 citations
882. Chinese Synesthesia Detection: New Dataset and ModelsFindings7 citations
883. Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-SpeechLong7 citations
884. DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-trainingFindings7 citations
885. Data Augmentation and Learned Layer Aggregation for Improved Multilingual Language Understanding in DialogueFindings7 citations
886. EICO: Improving Few-Shot Text Classification via Explicit and Implicit Consistency RegularizationFindings7 citations
887. EnCBP: A New Benchmark Dataset for Finer-Grained Cultural Background Prediction in EnglishFindings7 citations
888. Exploring the Capacity of a Large-scale Masked Language Model to Recognize Grammatical ErrorsFindings7 citations
889. Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERTLong7 citations
890. Going “Deeper”: Structured Sememe Prediction via Transformer with Tree AttentionFindings7 citations
891. HOLM: Hallucinating Objects with Language Models for Referring Expression Recognition in Partially-Observed ScenesLong7 citations
892. Hybrid Semantics for Goal-Directed Natural Language GenerationLong7 citations
893. Interpreting Character Embeddings With Perceptual Representations: The Case of Shape, Sound, and ColorLong7 citations
894. Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine ComprehensionLong7 citations
895. Multilingual unsupervised sequence segmentation transfers to extremely low-resource languagesLong7 citations
896. Neural Label Search for Zero-Shot Multi-Lingual Extractive SummarizationLong7 citations
897. Phone-ing it in: Towards Flexible Multi-Modal Language Model Training by Phonetic Representations of DataLong7 citations
898. Probing Multilingual Cognate Prediction ModelsFindings7 citations
899. RuCCoN: Clinical Concept Normalization in RussianFindings7 citations
900. Triangular Transfer: Freezing the Pivot for Triangular Machine TranslationShort7 citations
901. TwittIrish: A Universal Dependencies Treebank of Tweets in Modern IrishLong7 citations
902. Which side are you on? Insider-Outsider classification in conspiracy-theoretic social mediaLong7 citations
903. Adversarial Authorship Attribution for DeobfuscationLong6 citations
904. C-MORE: Pretraining to Answer Open-Domain Questions by Consulting Millions of ReferencesShort6 citations
905. CAMERO: Consistency Regularized Ensemble of Perturbed Language Models with Weight SharingLong6 citations
906. CUE Vectors: Modular Training of Language Models Conditioned on Diverse Contextual SignalsFindings6 citations
907. Can Synthetic Translations Improve Bitext Quality?Long6 citations
908. Combining (Second-Order) Graph-Based and Headed-Span-Based Projective Dependency ParsingFindings6 citations
909. Cross-Lingual Phrase RetrievalLong6 citations
910. Detecting Unassimilated Borrowings in Spanish: An Annotated Corpus and Approaches to ModelingLong6 citations
911. Developmental Negation Processing in Transformer Language ModelsShort6 citations
912. Dual Context-Guided Continuous Prompt Tuning for Few-Shot LearningFindings6 citations
913. Flexible Generation from Fragmentary Linguistic InputLong6 citations
914. Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine TranslationShort6 citations
915. From Stance to Concern: Adaptation of Propositional Analysis to New Tasks and DomainsFindings6 citations
916. Implicit Relation Linking for Question Answering over Knowledge GraphFindings6 citations
917. KSAM: Infusing Multi-Source Knowledge into Dialogue Generation via Knowledge Source Aware Multi-Head DecodingFindings6 citations
918. Knowledge Graph Embedding by Adaptive Limit Scoring Loss Using Dynamic Weighting StrategyFindings6 citations
919. Letters From the Past: Modeling Historical Sound Change Through Diachronic Character EmbeddingsLong6 citations
920. Lexical Knowledge Internalization for Neural Dialog GenerationLong6 citations
921. MPII: Multi-Level Mutual Promotion for Inference and InterpretationLong6 citations
922. Mitigating the Inconsistency Between Word Saliency and Model Confidence with Pathological Contrastive TrainingFindings6 citations
923. Modeling U.S. State-Level Policies by Extracting Winners and Losers from Legislative TextsLong6 citations
924. On the data requirements of probingFindings6 citations
925. Phoneme transcription of endangered languages: an evaluation of recent ASR architectures in the single speaker scenarioFindings6 citations
926. Ranking-Constrained Learning with Rationales for Text ClassificationFindings6 citations
927. Rewarding Semantic Similarity under Optimized Alignments for AMR-to-Text GenerationShort6 citations
928. Searching for fingerspelled content in American Sign LanguageLong6 citations
929. Thai Nested Named Entity Recognition CorpusFindings6 citations
930. Weakly Supervised Word Segmentation for Computational Language DocumentationLong6 citations
931. Aligned Weight Regularizers for Pruning Pretrained Neural NetworksFindings5 citations
932. Auxiliary tasks to boost Biaffine Semantic Dependency ParsingFindings5 citations
933. CoDA21: Evaluating Language Understanding Capabilities of NLP Models With Context-Definition AlignmentShort5 citations
934. Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language ModelFindings5 citations
935. Down and Across: Introducing Crossword-Solving as a New NLP BenchmarkLong5 citations
936. Exploiting Language Model Prompts Using Similarity Measures: A Case Study on the Word-in-Context TaskShort5 citations
937. From BERT‘s Point of View: Revealing the Prevailing Contextual DifferencesFindings5 citations
938. How Can Cross-lingual Knowledge Contribute Better to Fine-Grained Entity Typing?Findings5 citations
939. Leveraging Explicit Lexico-logical Alignments in Text-to-SQL ParsingShort5 citations
940. Modeling Syntactic-Semantic Dependency Correlations in Semantic Role Labeling Using Mixture ModelsLong5 citations
941. Multi-Scale Distribution Deep Variational Autoencoder for Explanation GenerationFindings5 citations
942. OneAligner: Zero-shot Cross-lingual Transfer with One Rich-Resource Language Pair for Low-Resource Sentence RetrievalFindings5 citations
943. Predicting Intervention Approval in Clinical Trials through Multi-Document SummarizationLong5 citations
944. Rethinking Offensive Text Detection as a Multi-Hop Reasoning ProblemFindings5 citations
945. Semi-supervised Domain Adaptation for Dependency Parsing with Dynamic Matching NetworkLong5 citations
946. Single Model Ensemble for Subword Regularized Models in Low-Resource Machine TranslationFindings5 citations
947. That Slepen Al the Nyght with Open Ye! Cross-era Sequence Segmentation with Switch-memoryLong5 citations
948. To Find Waldo You Need Contextual Cues: Debiasing Who’s WaldoShort5 citations
949. Transfer Learning and Prediction Consistency for Detecting Offensive Spans of TextFindings5 citations
950. Transformers in the loop: Polarity in neural models of languageLong5 citations
951. Unsupervised Chinese Word Segmentation with BERT Oriented Probing and TransformationFindings5 citations
952. Using NLP to quantify the environmental cost and diversity benefits of in-person NLP conferencesFindings5 citations
953. Weighted self Distillation for Chinese word segmentationFindings5 citations
954. CaMEL: Case Marker Extraction without LabelsLong4 citations
955. Can Visual Dialogue Models Do Scorekeeping? Exploring How Dialogue Representations Incrementally Encode Shared KnowledgeShort4 citations
956. Composing Structure-Aware Batches for Pairwise Sentence ClassificationFindings4 citations
957. Controlling the Focus of Pretrained Language Generation ModelsFindings4 citations
958. Cross-Lingual UMLS Named Entity Linking using UMLS Dictionary Fine-TuningFindings4 citations
959. Domain Adaptation in Multilingual and Multi-Domain Monolingual Settings for Complex Word IdentificationLong4 citations
960. EAG: Extract and Generate Multi-way Aligned Corpus for Complete Multi-lingual Neural Machine TranslationLong4 citations
961. Feeding What You Need by Understanding What You LearnedLong4 citations
962. Focus on the Action: Learning to Highlight and Summarize Jointly for Email To-Do Items SummarizationFindings4 citations
963. HYPHEN: Hyperbolic Hawkes Attention For Text StreamsShort4 citations
964. How Distributed are Distributed Representations? An Observation on the Locality of Syntactic Information in Verb Agreement TasksShort4 citations
965. Input-specific Attention Subnetworks for Adversarial DetectionFindings4 citations
966. Interactive Word Completion for Plains CreeLong4 citations
967. Investigating Data Variance in Evaluations of Automatic Machine Translation MetricsFindings4 citations
968. Investigating person-specific errors in chat-oriented dialogue systemsShort4 citations
969. Learning-by-Narrating: Narrative Pre-Training for Zero-Shot Dialogue ComprehensionShort4 citations
970. Leveraging Relaxed Equilibrium by Lazy Transition for Sequence ModelingLong4 citations
971. Lite Unified Modeling for Discriminative Reading ComprehensionLong4 citations
972. On Length Divergence Bias in Textual Matching ModelsFindings4 citations
973. Pixie: Preference in Implicit and Explicit ComparisonsShort4 citations
974. Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and EfficiencyLong4 citations
975. Self-supervised Semantic-driven Phoneme Discovery for Zero-resource Speech RecognitionLong4 citations
976. Sub-Word Alignment is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine TranslationShort4 citations
977. Task-guided Disentangled Tuning for Pretrained Language ModelsFindings4 citations
978. TopWORDS-Seg: Simultaneous Text Segmentation and Word Discovery for Open-Domain Chinese Texts via Bayesian InferenceLong4 citations
979. Two-Step Question Retrieval for Open-Domain QAFindings4 citations
980. Word-level Perturbation Considering Word Length and Compositional SubwordsFindings4 citations
981. A Copy-Augmented Generative Model for Open-Domain Question AnsweringShort3 citations
982. A Flexible Multi-Task Model for BERT ServingShort3 citations
983. Addressing Resource and Privacy Constraints in Semantic Parsing Through Data AugmentationFindings3 citations
984. Attention Mechanism with Energy-Friendly OperationsFindings3 citations
985. CaM-Gen: Causally Aware Metric-Guided Text GenerationFindings3 citations
986. Co-training an Unsupervised Constituency Parser with Weak SupervisionFindings3 citations
987. Dependency-based Mixture Language ModelsLong3 citations
988. Hierarchical Inductive Transfer for Continual Dialogue LearningFindings3 citations
989. Interpretable Research Replication Prediction via Variational Contextual Consistency Sentence MaskingFindings3 citations
990. LM-BFF-MS: Improving Few-Shot Fine-tuning of Language Models based on Multiple Soft Demonstration MemoryShort3 citations
991. More Than Words: Collocation Retokenization for Latent Dirichlet Allocation ModelsFindings3 citations
992. On Controlling Fallback Responses for Grounded Dialogue GenerationFindings3 citations
993. Region-dependent temperature scaling for certainty calibration and application to class-imbalanced token classificationShort3 citations
994. Revisiting the Effects of Leakage on Dependency ParsingFindings3 citations
995. Suum Cuique: Studying Bias in Taboo Detection with a Community PerspectiveFindings3 citations
996. Synchronous Refinement for Neural Machine TranslationFindings3 citations
997. Visualizing the Relationship Between Encoded Linguistic Information and Task PerformanceFindings3 citations
998. XDBERT: Distilling Visual Information to BERT from Cross-Modal Systems to Improve Language UnderstandingShort3 citations
999. ASCM: An Answer Space Clustered Prompting Method without Answer EngineeringFindings2 citations
1000. Accurate Online Posterior Alignments for Principled Lexically-Constrained DecodingLong2 citations

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