ACL 2023 Accepted Papers

The full list of 2,052 papers accepted at ACL 2023 (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. Self-Instruct: Aligning Language Models with Self-Generated InstructionsLong2,098 citations
2. NusaCrowd: Open Source Initiative for Indonesian NLP ResourcesFindings1,114 citations
3. Towards Reasoning in Large Language Models: A SurveyFindings818 citations
4. Crosslingual Generalization through Multitask FinetuningLong770 citations
5. Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve ThemFindings698 citations
6. Can Large Language Models Be an Alternative to Human Evaluations?Long560 citations
7. Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model SizesFindings501 citations
8. When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric MemoriesLong501 citations
9. Why Can GPT Learn In-Context? Language Models Secretly Perform Gradient Descent as Meta-OptimizersFindings421 citations
10. Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step QuestionsLong382 citations
11. MathPrompter: Mathematical Reasoning using Large Language ModelsIndustry344 citations
12. DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative ModelsLong340 citations
13. Large Language Models Are Reasoning TeachersLong338 citations
14. Unnatural Instructions: Tuning Language Models with (Almost) No Human LaborLong329 citations
15. Contrastive Decoding: Open-ended Text Generation as OptimizationLong322 citations
16. LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative FusionLong321 citations
17. Precise Zero-Shot Dense Retrieval without Relevance LabelsLong309 citations
18. Reasoning with Language Model Prompting: A SurveyLong301 citations
19. RARR: Researching and Revising What Language Models Say, Using Language ModelsLong297 citations
20. Discovering Language Model Behaviors with Model-Written EvaluationsFindings290 citations
21. One Embedder, Any Task: Instruction-Finetuned Text EmbeddingsFindings287 citations
22. Teaching Small Language Models to ReasonShort265 citations
23. From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP ModelsLong256 citations
24. Is GPT-3 a Good Data Annotator?Long256 citations
25. Revisiting Relation Extraction in the era of Large Language ModelsLong240 citations
26. Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language ModelsLong229 citations
27. In-context Examples Selection for Machine TranslationFindings213 citations
28. Do Large Language Models Know What They Don’t Know?Findings208 citations
29. Knowledge Unlearning for Mitigating Privacy Risks in Language ModelsLong202 citations
30. Evaluating Open-Domain Question Answering in the Era of Large Language ModelsLong198 citations
31. On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot ReasoningLong197 citations
32. Making Language Models Better Reasoners with Step-Aware VerifierLong185 citations
33. Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language ModelsLong180 citations
34. Membership Inference Attacks against Language Models via Neighbourhood ComparisonFindings180 citations
35. Large Language Models Meet NL2Code: A SurveyLong177 citations
36. What the DAAM: Interpreting Stable Diffusion Using Cross AttentionLong171 citations
37. Prompting PaLM for Translation: Assessing Strategies and PerformanceLong170 citations
38. A Length-Extrapolatable TransformerLong166 citations
39. A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark DatasetsFindings165 citations
40. AlignScore: Evaluating Factual Consistency with A Unified Alignment FunctionLong158 citations
41. Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought FrameworkLong155 citations
42. A Survey of Deep Learning for Mathematical ReasoningLong152 citations
43. Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and OrderingLong151 citations
44. Instruction Induction: From Few Examples to Natural Language Task DescriptionsLong148 citations
45. Large Language Models with Controllable Working MemoryFindings148 citations
46. Reasoning Implicit Sentiment with Chain-of-Thought PromptingShort145 citations
47. Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and EvaluationFindings138 citations
48. Diverse Demonstrations Improve In-context Compositional GeneralizationLong136 citations
49. Distilling Reasoning Capabilities into Smaller Language ModelsFindings135 citations
50. Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human InterventionsLong135 citations
51. Analyzing Transformers in Embedding SpaceLong133 citations
52. Unified Demonstration Retriever for In-Context LearningLong133 citations
53. Revealing Single Frame Bias for Video-and-Language LearningLong132 citations
54. Fact-Checking Complex Claims with Program-Guided ReasoningLong126 citations
55. DiffusionBERT: Improving Generative Masked Language Models with Diffusion ModelsLong125 citations
56. Symbolic Chain-of-Thought Distillation: Small Models Can Also “Think” Step-by-StepLong124 citations
57. MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse LanguagesLong123 citations
58. Self-Edit: Fault-Aware Code Editor for Code GenerationLong121 citations
59. Evaluating the Factual Consistency of Large Language Models Through News SummarizationFindings118 citations
60. NUWA-XL: Diffusion over Diffusion for eXtremely Long Video GenerationLong118 citations
61. MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction TuningLong117 citations
62. Parallel Context Windows for Large Language ModelsLong116 citations
63. Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human EvaluationLong116 citations
64. SimLM: Pre-training with Representation Bottleneck for Dense Passage RetrievalLong114 citations
65. Few-shot In-context Learning on Knowledge Base Question AnsweringLong113 citations
66. Task-aware Retrieval with InstructionsFindings111 citations
67. RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model OutputsLong106 citations
68. DePlot: One-shot visual language reasoning by plot-to-table translationFindings105 citations
69. FedPETuning: When Federated Learning Meets the Parameter-Efficient Tuning Methods of Pre-trained Language ModelsFindings103 citations
70. SCOTT: Self-Consistent Chain-of-Thought DistillationLong103 citations
71. Sequence Parallelism: Long Sequence Training from System PerspectiveLong102 citations
72. Unlearning Bias in Language Models by Partitioning GradientsFindings102 citations
73. Don’t Generate, Discriminate: A Proposal for Grounding Language Models to Real-World EnvironmentsLong100 citations
74. What In-Context Learning “Learns” In-Context: Disentangling Task Recognition and Task LearningFindings100 citations
75. Knowledge of cultural moral norms in large language modelsLong98 citations
76. Randomized Positional Encodings Boost Length Generalization of TransformersShort97 citations
77. Solving Math Word Problems via Cooperative Reasoning induced Language ModelsLong97 citations
78. Synthetic Text Generation with Differential Privacy: A Simple and Practical RecipeLong97 citations
79. Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What MattersLong95 citations
80. Federated Learning of Gboard Language Models with Differential PrivacyIndustry94 citations
81. MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart DerenderingLong94 citations
82. “Low-Resource” Text Classification: A Parameter-Free Classification Method with CompressorsFindings94 citations
83. Code4Struct: Code Generation for Few-Shot Event Structure PredictionLong92 citations
84. WinoQueer: A Community-in-the-Loop Benchmark for Anti-LGBTQ+ Bias in Large Language ModelsLong92 citations
85. A Critical Evaluation of Evaluations for Long-form Question AnsweringLong91 citations
86. GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-Distribution Generalization PerspectiveFindings90 citations
87. Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene HallucinationLong90 citations
88. Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error DetectorsLong89 citations
89. A fine-grained comparison of pragmatic language understanding in humans and language modelsLong88 citations
90. Glot500: Scaling Multilingual Corpora and Language Models to 500 LanguagesLong88 citations
91. AVATAR: A Parallel Corpus for Java-Python Program TranslationFindings87 citations
92. Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic ModelingLong87 citations
93. ConFEDE: Contrastive Feature Decomposition for Multimodal Sentiment AnalysisLong86 citations
94. LAMBADA: Backward Chaining for Automated Reasoning in Natural LanguageLong86 citations
95. SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular ControlLong86 citations
96. Do Androids Laugh at Electric Sheep? Humor “Understanding” Benchmarks from The New Yorker Caption ContestLong85 citations
97. WebCPM: Interactive Web Search for Chinese Long-form Question AnsweringLong85 citations
98. AltCLIP: Altering the Language Encoder in CLIP for Extended Language CapabilitiesFindings84 citations
99. Complementary Explanations for Effective In-Context LearningFindings83 citations
100. Accelerating Transformer Inference for Translation via Parallel DecodingLong82 citations
101. Cognitive Reframing of Negative Thoughts through Human-Language Model InteractionLong82 citations
102. Factually Consistent Summarization via Reinforcement Learning with Textual Entailment FeedbackLong82 citations
103. Robust Multi-bit Natural Language Watermarking through Invariant FeaturesLong82 citations
104. MolXPT: Wrapping Molecules with Text for Generative Pre-trainingShort81 citations
105. VisText: A Benchmark for Semantically Rich Chart CaptioningLong81 citations
106. CodeIE: Large Code Generation Models are Better Few-Shot Information ExtractorsLong79 citations
107. Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language ModelsLong79 citations
108. Minding Language Models’ (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief TrackerLong77 citations
109. Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation ExtractorsFindings76 citations
110. NLPositionality: Characterizing Design Biases of Datasets and ModelsLong76 citations
111. DISCO: Distilling Counterfactuals with Large Language ModelsLong75 citations
112. Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought MethodLong75 citations
113. Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected KnowledgeLong74 citations
114. DOC: Improving Long Story Coherence With Detailed Outline ControlLong73 citations
115. Limitations of Language Models in Arithmetic and Symbolic InductionLong72 citations
116. Prompted LLMs as Chatbot Modules for Long Open-domain ConversationFindings72 citations
117. Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic LanguagesLong72 citations
118. KGA: A General Machine Unlearning Framework Based on Knowledge Gap AlignmentLong71 citations
119. Nonparametric Masked Language ModelingFindings71 citations
120. Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted AlignmentLong70 citations
121. MvP: Multi-view Prompting Improves Aspect Sentiment Tuple PredictionLong70 citations
122. Character-Aware Models Improve Visual Text RenderingLong67 citations
123. Faithfulness Tests for Natural Language ExplanationsShort67 citations
124. BLOOM+1: Adding Language Support to BLOOM for Zero-Shot PromptingLong66 citations
125. DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question AnsweringLong66 citations
126. Multiview Identifiers Enhanced Generative RetrievalLong66 citations
127. DiffusionNER: Boundary Diffusion for Named Entity RecognitionLong65 citations
128. Data Curation Alone Can Stabilize In-context LearningLong64 citations
129. Faking Fake News for Real Fake News Detection: Propaganda-Loaded Training Data GenerationLong64 citations
130. LENS: A Learnable Evaluation Metric for Text SimplificationLong64 citations
131. Mitigating Label Biases for In-context LearningLong64 citations
132. Natural Language to Code Generation in Interactive Data Science NotebooksLong64 citations
133. DiaASQ: A Benchmark of Conversational Aspect-based Sentiment Quadruple AnalysisFindings63 citations
134. FactKG: Fact Verification via Reasoning on Knowledge GraphsLong62 citations
135. Generating Visual Spatial Description via Holistic 3D Scene UnderstandingLong62 citations
136. ReCode: Robustness Evaluation of Code Generation ModelsLong62 citations
137. ML-LMCL: Mutual Learning and Large-Margin Contrastive Learning for Improving ASR Robustness in Spoken Language UnderstandingFindings61 citations
138. Z-ICL: Zero-Shot In-Context Learning with Pseudo-DemonstrationsLong61 citations
139. AugESC: Dialogue Augmentation with Large Language Models for Emotional Support ConversationFindings60 citations
140. Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-InLong60 citations
141. Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even BetterLong60 citations
142. Supervised Adversarial Contrastive Learning for Emotion Recognition in ConversationsLong60 citations
143. A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language ModelsLong59 citations
144. Large Language Models are Built-in Autoregressive Search EnginesFindings59 citations
145. Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM’s Translation CapabilityLong59 citations
146. Summarizing, Simplifying, and Synthesizing Medical Evidence using GPT-3 (with Varying Success)Short59 citations
147. Modular Visual Question Answering via Code GenerationShort58 citations
148. RHO: Reducing Hallucination in Open-domain Dialogues with Knowledge GroundingFindings58 citations
149. Z-Code++: A Pre-trained Language Model Optimized for Abstractive SummarizationLong58 citations
150. Better Zero-Shot Reasoning with Self-Adaptive PromptingFindings57 citations
151. Coupling Large Language Models with Logic Programming for Robust and General Reasoning from TextFindings57 citations
152. LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model DevelopmentLong57 citations
153. MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain ConversationLong57 citations
154. Patton: Language Model Pretraining on Text-Rich NetworksLong57 citations
155. Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion ScaleLong57 citations
156. ColD Fusion: Collaborative Descent for Distributed Multitask FinetuningLong56 citations
157. Multi-target Backdoor Attacks for Code Pre-trained ModelsLong56 citations
158. DualGATs: Dual Graph Attention Networks for Emotion Recognition in ConversationsLong55 citations
159. Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context LearningFindings55 citations
160. Prompted Opinion Summarization with GPT-3.5Findings55 citations
161. MultiEMO: An Attention-Based Correlation-Aware Multimodal Fusion Framework for Emotion Recognition in ConversationsLong54 citations
162. Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole SentenceFindings54 citations
163. A Close Look into the Calibration of Pre-trained Language ModelsLong53 citations
164. ConvGQR: Generative Query Reformulation for Conversational SearchLong53 citations
165. DrBERT: A Robust Pre-trained Model in French for Biomedical and Clinical domainsLong53 citations
166. Towards Robust Ranker for Text RetrievalFindings53 citations
167. A Survey for Efficient Open Domain Question AnsweringLong52 citations
168. Causal Intervention and Counterfactual Reasoning for Multi-modal Fake News DetectionLong52 citations
169. How Do In-Context Examples Affect Compositional Generalization?Long52 citations
170. Parameter-Efficient Fine-Tuning without Introducing New LatencyLong52 citations
171. An Embarrassingly Easy but Strong Baseline for Nested Named Entity RecognitionShort51 citations
172. Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor WatermarkLong51 citations
173. NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP ModelsLong51 citations
174. Trillion Dollar Words: A New Financial Dataset, Task & Market AnalysisLong51 citations
175. Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft PromptingFindings50 citations
176. Exploring the Effectiveness of Prompt Engineering for Legal Reasoning TasksFindings50 citations
177. MeetingBank: A Benchmark Dataset for Meeting SummarizationLong50 citations
178. The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and ChallengesFindings50 citations
179. Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense KnowledgeLong49 citations
180. TECHS: Temporal Logical Graph Networks for Explainable Extrapolation ReasoningLong49 citations
181. Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue SystemFindings49 citations
182. CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response GenerationLong48 citations
183. I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual MetaphorsFindings48 citations
184. Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data AugmentationLong48 citations
185. Multilingual Summarization with Factual Consistency EvaluationFindings48 citations
186. NormBank: A Knowledge Bank of Situational Social NormsLong48 citations
187. Pre-trained Language Models Can be Fully Zero-Shot LearnersLong48 citations
188. UnitY: Two-pass Direct Speech-to-speech Translation with Discrete UnitsLong48 citations
189. Enhancing Document-level Event Argument Extraction with Contextual Clues and Role RelevanceFindings47 citations
190. Event Extraction as Question Generation and AnsweringShort47 citations
191. Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support ConversationsLong47 citations
192. PromptNER: Prompt Locating and Typing for Named Entity RecognitionLong47 citations
193. Residual Prompt Tuning: improving prompt tuning with residual reparameterizationFindings47 citations
194. Sequential Integrated Gradients: a simple but effective method for explaining language modelsFindings47 citations
195. XL-LEXEME: WiC Pretrained Model for Cross-Lingual LEXical sEMantic changEShort47 citations
196. Code Execution with Pre-trained Language ModelsFindings46 citations
197. Detecting Edit Failures In Large Language Models: An Improved Specificity BenchmarkFindings46 citations
198. Grokking of Hierarchical Structure in Vanilla TransformersShort46 citations
199. Multi-VALUE: A Framework for Cross-Dialectal English NLPLong46 citations
200. Multilingual LLMs are Better Cross-lingual In-context Learners with AlignmentLong46 citations
201. Understanding In-Context Learning via Supportive Pretraining DataLong46 citations
202. ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?Short45 citations
203. Distilling Script Knowledge from Large Language Models for Constrained Language PlanningLong45 citations
204. Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models’ MemoriesLong45 citations
205. Scientific Fact-Checking: A Survey of Resources and ApproachesFindings45 citations
206. BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language ModelsFindings44 citations
207. How poor is the stimulus? Evaluating hierarchical generalization in neural networks trained on child-directed speechLong44 citations
208. Improving Gender Fairness of Pre-Trained Language Models without Catastrophic ForgettingShort44 citations
209. Retrieve-and-Sample: Document-level Event Argument Extraction via Hybrid Retrieval AugmentationLong44 citations
210. A Formal Perspective on Byte-Pair EncodingFindings43 citations
211. BITE: Textual Backdoor Attacks with Iterative Trigger InjectionLong43 citations
212. DarkBERT: A Language Model for the Dark Side of the InternetLong43 citations
213. DiffuSum: Generation Enhanced Extractive Summarization with DiffusionFindings43 citations
214. A Customized Text Sanitization Mechanism with Differential PrivacyFindings42 citations
215. DP-BART for Privatized Text Rewriting under Local Differential PrivacyFindings42 citations
216. Does GPT-3 Grasp Metaphors? Identifying Metaphor Mappings with Generative Language ModelsLong42 citations
217. On Improving Summarization Factual Consistency from Natural Language FeedbackLong42 citations
218. Pre-Training to Learn in ContextLong42 citations
219. Cold-Start Data Selection for Better Few-shot Language Model Fine-tuning: A Prompt-based Uncertainty Propagation ApproachLong41 citations
220. KoSBI: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model ApplicationsIndustry41 citations
221. Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedbackLong41 citations
222. Pre-trained Language Model with Prompts for Temporal Knowledge Graph CompletionFindings41 citations
223. Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack FrameworkFindings40 citations
224. Causal-Debias: Unifying Debiasing in Pretrained Language Models and Fine-tuning via Causal Invariant LearningLong40 citations
225. Considerations for meaningful sign language machine translation based on glossesShort40 citations
226. CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language PairsLong40 citations
227. Dissecting Transformer Length Extrapolation via the Lens of Receptive Field AnalysisLong40 citations
228. ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming LanguagesFindings40 citations
229. Entity Tracking in Language ModelsLong40 citations
230. Exploring Zero and Few-shot Techniques for Intent ClassificationIndustry40 citations
231. MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection SystemFindings40 citations
232. On the Expressivity Role of LayerNorm in Transformers’ AttentionFindings40 citations
233. Controlling the Extraction of Memorized Data from Large Language Models via Prompt-TuningShort39 citations
234. Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction TuningShort39 citations
235. Gloss-Free End-to-End Sign Language TranslationLong39 citations
236. Improving Contrastive Learning of Sentence Embeddings from AI FeedbackFindings39 citations
237. Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data InterventionsShort39 citations
238. NLPeer: A Unified Resource for the Computational Study of Peer ReviewLong39 citations
239. Open-Domain Hierarchical Event Schema Induction by Incremental Prompting and VerificationLong39 citations
240. SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative ModelsLong39 citations
241. Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean FunctionsLong39 citations
242. The Elephant in the Room: Analyzing the Presence of Big Tech in Natural Language Processing ResearchLong39 citations
243. What Do NLP Researchers Believe? Results of the NLP Community MetasurveyLong39 citations
244. Zero-shot Faithful Factual Error CorrectionLong39 citations
245. AoM: Detecting Aspect-oriented Information for Multimodal Aspect-Based Sentiment AnalysisFindings38 citations
246. Compounding Geometric Operations for Knowledge Graph CompletionLong38 citations
247. FORK: A Bite-Sized Test Set for Probing Culinary Cultural Biases in Commonsense Reasoning ModelsFindings38 citations
248. Learning Latent Relations for Temporal Knowledge Graph ReasoningLong38 citations
249. Rehearsal-free Continual Language Learning via Efficient Parameter IsolationLong38 citations
250. Tokenization and the Noiseless ChannelLong38 citations
251. BIC: Twitter Bot Detection with Text-Graph Interaction and Semantic ConsistencyLong37 citations
252. Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-ExpertsShort37 citations
253. Dynamic Routing Transformer Network for Multimodal Sarcasm DetectionLong37 citations
254. ETHICIST: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence EstimationLong37 citations
255. Learning In-context Learning for Named Entity RecognitionLong37 citations
256. MVP: Multi-task Supervised Pre-training for Natural Language GenerationFindings37 citations
257. On the Blind Spots of Model-Based Evaluation Metrics for Text GenerationLong37 citations
258. AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction ModelLong36 citations
259. Cross-Lingual Retrieval Augmented Prompt for Low-Resource LanguagesFindings36 citations
260. Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction LearningLong36 citations
261. Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk DecodingFindings36 citations
262. PAED: Zero-Shot Persona Attribute Extraction in DialoguesLong36 citations
263. RankCSE: Unsupervised Sentence Representations Learning via Learning to RankLong36 citations
264. Critic-Guided Decoding for Controlled Text GenerationFindings35 citations
265. Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-trainingLong35 citations
266. DT-Solver: Automated Theorem Proving with Dynamic-Tree Sampling Guided by Proof-level Value FunctionLong35 citations
267. Graph Reasoning for Question Answering with Triplet RetrievalFindings35 citations
268. Multi-granularity Temporal Question Answering over Knowledge GraphsLong35 citations
269. ORGAN: Observation-Guided Radiology Report Generation via Tree ReasoningLong35 citations
270. Speaking Multiple Languages Affects the Moral Bias of Language ModelsFindings35 citations
271. Structured Pruning for Efficient Generative Pre-trained Language ModelsFindings35 citations
272. Tab-CoT: Zero-shot Tabular Chain of ThoughtFindings35 citations
273. The CRINGE Loss: Learning what language not to modelLong35 citations
274. A Better Way to Do Masked Language Model ScoringShort34 citations
275. ANALOGICAL - A Novel Benchmark for Long Text Analogy Evaluation in Large Language ModelsFindings34 citations
276. Backdooring Neural Code SearchLong34 citations
277. COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive StatementsFindings34 citations
278. Chain of Thought Prompting Elicits Knowledge AugmentationFindings34 citations
279. ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral SituationsLong34 citations
280. DICE: Data-Efficient Clinical Event Extraction with Generative ModelsLong34 citations
281. How Well Do Large Language Models Perform on Faux Pas Tests?Findings34 citations
282. Improved Logical Reasoning of Language Models via Differentiable Symbolic ProgrammingFindings34 citations
283. MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema ModelingLong34 citations
284. PromptRank: Unsupervised Keyphrase Extraction Using PromptLong34 citations
285. Prompting Language Models for Linguistic StructureLong34 citations
286. ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense RetrievalFindings34 citations
287. SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding TasksLong34 citations
288. SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech TranslationsLong34 citations
289. Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image ModelsFindings34 citations
290. Tailor: A Soft-Prompt-Based Approach to Attribute-Based Controlled Text GenerationLong34 citations
291. The Dangers of trusting Stochastic Parrots: Faithfulness and Trust in Open-domain Conversational Question AnsweringFindings34 citations
292. This prompt is measuring <mask>: evaluating bias evaluation in language modelsFindings34 citations
293. Toward Human-Like Evaluation for Natural Language Generation with Error AnalysisLong34 citations
294. When Does Translation Require Context? A Data-driven, Multilingual ExplorationLong34 citations
295. A Measure-Theoretic Characterization of Tight Language ModelsLong33 citations
296. Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue ModelsFindings33 citations
297. CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector RetrievalLong33 citations
298. DisorBERT: A Double Domain Adaptation Model for Detecting Signs of Mental Disorders in Social MediaLong33 citations
299. Efficient Transformers with Dynamic Token PoolingLong33 citations
300. Explaining How Transformers Use Context to Build PredictionsLong33 citations
301. In-Context Analogical Reasoning with Pre-Trained Language ModelsLong33 citations
302. Language acquisition: do children and language models follow similar learning stages?Findings33 citations
303. MetaAdapt: Domain Adaptive Few-Shot Misinformation Detection via Meta LearningLong33 citations
304. Multilingual Multifaceted Understanding of Online News in Terms of Genre, Framing, and Persuasion TechniquesLong33 citations
305. UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based RecommendationShort33 citations
306. Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-TrainingFindings33 citations
307. What Are You Token About? Dense Retrieval as Distributions Over the VocabularyLong33 citations
308. A Cross-Modality Context Fusion and Semantic Refinement Network for Emotion Recognition in ConversationLong32 citations
309. A Facial Expression-Aware Multimodal Multi-task Learning Framework for Emotion Recognition in Multi-party ConversationsLong32 citations
310. Counterfactual Debiasing for Fact VerificationLong32 citations
311. Direct Fact Retrieval from Knowledge Graphs without Entity LinkingLong32 citations
312. Do PLMs Know and Understand Ontological Knowledge?Long32 citations
313. Exploring Continual Learning for Code Generation ModelsShort32 citations
314. FiDO: Fusion-in-Decoder optimized for stronger performance and faster inferenceFindings32 citations
315. Gender-tuning: Empowering Fine-tuning for Debiasing Pre-trained Language ModelsFindings32 citations
316. I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-ImitationLong32 citations
317. MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & TasksLong32 citations
318. RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial PerturbationsLong32 citations
319. Small Data, Big Impact: Leveraging Minimal Data for Effective Machine TranslationLong32 citations
320. T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image GenerationFindings32 citations
321. Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-text RationalesLong31 citations
322. Credible without Credit: Domain Experts Assess Generative Language ModelsShort31 citations
323. Don’t Lose Yourself! Empathetic Response Generation via Explicit Self-Other AwarenessFindings31 citations
324. EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive PruningFindings31 citations
325. Explainable Recommendation with Personalized Review Retrieval and Aspect LearningLong31 citations
326. Grounded Multimodal Named Entity Recognition on Social MediaLong31 citations
327. Learn over Past, Evolve for Future: Forecasting Temporal Trends for Fake News DetectionIndustry31 citations
328. Measuring Inductive Biases of In-Context Learning with Underspecified DemonstrationsLong31 citations
329. MixPAVE: Mix-Prompt Tuning for Few-shot Product Attribute Value ExtractionFindings31 citations
330. PAL: Persona-Augmented Emotional Support Conversation GenerationFindings31 citations
331. Prototype-Guided Pseudo Labeling for Semi-Supervised Text ClassificationLong31 citations
332. S2ynRE: Two-stage Self-training with Synthetic data for Low-resource Relation ExtractionLong31 citations
333. TOME: A Two-stage Approach for Model-based RetrievalLong31 citations
334. TemplateGEC: Improving Grammatical Error Correction with Detection TemplateLong31 citations
335. The Larger they are, the Harder they Fail: Language Models do not Recognize Identifier Swaps in PythonFindings31 citations
336. ThinkSum: Probabilistic reasoning over sets using large language modelsLong31 citations
337. An AMR-based Link Prediction Approach for Document-level Event Argument ExtractionLong30 citations
338. CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal GroundingLong30 citations
339. DecompX: Explaining Transformers Decisions by Propagating Token DecompositionLong30 citations
340. DiscoPrompt: Path Prediction Prompt Tuning for Implicit Discourse Relation RecognitionFindings30 citations
341. Emergent Modularity in Pre-trained TransformersFindings30 citations
342. Environmental Claim DetectionShort30 citations
343. FairPrism: Evaluating Fairness-Related Harms in Text GenerationLong30 citations
344. HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text ClassificationLong30 citations
345. Improving Generalization in Language Model-based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-based TechniquesShort30 citations
346. PuMer: Pruning and Merging Tokens for Efficient Vision Language ModelsLong30 citations
347. RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation ExtractionLong30 citations
348. Rethinking Masked Language Modeling for Chinese Spelling CorrectionLong30 citations
349. Selecting Better Samples from Pre-trained LLMs: A Case Study on Question GenerationFindings30 citations
350. Tackling Modality Heterogeneity with Multi-View Calibration Network for Multimodal Sentiment DetectionLong30 citations
351. Towards a Common Understanding of Contributing Factors for Cross-Lingual Transfer in Multilingual Language Models: A ReviewLong30 citations
352. A Synthetic Data Generation Framework for Grounded DialoguesLong29 citations
353. An Effective Deployment of Contrastive Learning in Multi-label Text ClassificationFindings29 citations
354. An Open Dataset and Model for Language IdentificationShort29 citations
355. DLAMA: A Framework for Curating Culturally Diverse Facts for Probing the Knowledge of Pretrained Language ModelsFindings29 citations
356. Do GPTs Produce Less Literal Translations?Short29 citations
357. Exploring Large Language Models for Classical PhilologyLong29 citations
358. Facilitating Multi-turn Emotional Support Conversation with Positive Emotion Elicitation: A Reinforcement Learning ApproachLong29 citations
359. HINT: Hypernetwork Instruction Tuning for Efficient Zero- and Few-Shot GeneralisationLong29 citations
360. KILM: Knowledge Injection into Encoder-Decoder Language ModelsLong29 citations
361. MISGENDERED: Limits of Large Language Models in Understanding PronounsLong29 citations
362. REDFM: a Filtered and Multilingual Relation Extraction DatasetLong29 citations
363. Revisiting non-English Text Simplification: A Unified Multilingual BenchmarkLong29 citations
364. Social-Group-Agnostic Bias Mitigation via the Stereotype Content ModelLong29 citations
365. The Diminishing Returns of Masked Language Models to ScienceFindings29 citations
366. CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense ReasoningLong28 citations
367. CMOT: Cross-modal Mixup via Optimal Transport for Speech TranslationLong28 citations
368. Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the SpeakersLong28 citations
369. FACTIFY-5WQA: 5W Aspect-based Fact Verification through Question AnsweringLong28 citations
370. Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense KnowledgeFindings28 citations
371. Interpretable Multimodal Misinformation Detection with Logic ReasoningFindings28 citations
372. Not The End of Story: An Evaluation of ChatGPT-Driven Vulnerability Description MappingsFindings28 citations
373. PMAES: Prompt-mapping Contrastive Learning for Cross-prompt Automated Essay ScoringLong28 citations
374. RECAP: Retrieval-Enhanced Context-Aware Prefix Encoder for Personalized Dialogue Response GenerationLong28 citations
375. Revisiting Event Argument Extraction: Can EAE Models Learn Better When Being Aware of Event Co-occurrences?Long28 citations
376. Scaling in Cognitive Modelling: a Multilingual Approach to Human Reading TimesShort28 citations
377. Text Augmented Open Knowledge Graph Completion via Pre-Trained Language ModelsFindings28 citations
378. The Art of Prompting: Event Detection based on Type Specific PromptsShort28 citations
379. Towards Unified Spoken Language Understanding Decoding via Label-aware Compact Linguistics RepresentationsFindings28 citations
380. mCLIP: Multilingual CLIP via Cross-lingual TransferLong28 citations
381. A Fused Gromov-Wasserstein Framework for Unsupervised Knowledge Graph Entity AlignmentFindings27 citations
382. An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language ModelsLong27 citations
383. Benchmarking Large Language Model Capabilities for Conditional GenerationLong27 citations
384. ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language ModelsLong27 citations
385. Chain-of-Skills: A Configurable Model for Open-Domain Question AnsweringLong27 citations
386. DUB: Discrete Unit Back-translation for Speech TranslationFindings27 citations
387. Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive SummarizationLong27 citations
388. FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question AnsweringLong27 citations
389. HELP ME THINK: A Simple Prompting Strategy for Non-experts to Create Customized Content with ModelsFindings27 citations
390. Hierarchical Verbalizer for Few-Shot Hierarchical Text ClassificationLong27 citations
391. Is Anisotropy Truly Harmful? A Case Study on Text ClusteringShort27 citations
392. LMentry: A Language Model Benchmark of Elementary Language TasksFindings27 citations
393. Neural Machine Translation Methods for Translating Text to Sign Language GlossesLong27 citations
394. ORCA: A Challenging Benchmark for Arabic Language UnderstandingFindings27 citations
395. Prompt-Based Metric Learning for Few-Shot NERFindings27 citations
396. SERENGETI: Massively Multilingual Language Models for AfricaFindings27 citations
397. Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across LanguagesFindings27 citations
398. Understanding and Bridging the Modality Gap for Speech TranslationLong27 citations
399. (QA)2: Question Answering with Questionable AssumptionsLong26 citations
400. Augmenting Large Language Model Translators via Translation MemoriesFindings26 citations
401. BLIND: Bias Removal With No DemographicsLong26 citations
402. CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language ModelsLong26 citations
403. Click: Controllable Text Generation with Sequence Likelihood Contrastive LearningFindings26 citations
404. ConKI: Contrastive Knowledge Injection for Multimodal Sentiment AnalysisFindings26 citations
405. Controllable Mixed-Initiative Dialogue Generation through PromptingShort26 citations
406. I Cast Detect Thoughts: Learning to Converse and Guide with Intents and Theory-of-Mind in Dungeons and DragonsLong26 citations
407. Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain DetectionLong26 citations
408. LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-TuningShort26 citations
409. Multi-lingual and Multi-cultural Figurative Language UnderstandingFindings26 citations
410. MultiTool-CoT: GPT-3 Can Use Multiple External Tools with Chain of Thought PromptingShort26 citations
411. Multitask Pre-training of Modular Prompt for Chinese Few-Shot LearningLong26 citations
412. Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language ModelsFindings26 citations
413. Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured DataFindings26 citations
414. Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive EvaluationLong26 citations
415. TransESC: Smoothing Emotional Support Conversation via Turn-Level State TransitionFindings26 citations
416. Which Examples Should be Multiply Annotated? Active Learning When Annotators May DisagreeFindings26 citations
417. WhitenedCSE: Whitening-based Contrastive Learning of Sentence EmbeddingsLong26 citations
418. Adaptive and Personalized Exercise Generation for Online Language LearningLong25 citations
419. An Empirical Comparison of LM-based Question and Answer Generation MethodsFindings25 citations
420. An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical TextFindings25 citations
421. Backpack Language ModelsLong25 citations
422. Consistent Prototype Learning for Few-Shot Continual Relation ExtractionLong25 citations
423. Enhancing Personalized Dialogue Generation with Contrastive Latent Variables: Combining Sparse and Dense PersonaLong25 citations
424. GeoDRL: A Self-Learning Framework for Geometry Problem Solving using Reinforcement Learning in Deductive ReasoningFindings25 citations
425. Interpretable Word Sense Representations via Definition Generation: The Case of Semantic Change AnalysisLong25 citations
426. Language Anisotropic Cross-Lingual Model EditingFindings25 citations
427. MPCHAT: Towards Multimodal Persona-Grounded ConversationLong25 citations
428. Prompt- and Trait Relation-aware Cross-prompt Essay Trait ScoringFindings25 citations
429. Query-Efficient Black-Box Red Teaming via Bayesian OptimizationLong25 citations
430. RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the QuestionFindings25 citations
431. Reasoning in Large Language Models Through Symbolic Math Word ProblemsFindings25 citations
432. Summary-Oriented Vision Modeling for Multimodal Abstractive SummarizationLong25 citations
433. Towards Unifying Multi-Lingual and Cross-Lingual SummarizationLong25 citations
434. Understanding Differential Search Index for Text RetrievalFindings25 citations
435. A Survey on Asking Clarification Questions Datasets in Conversational SystemsLong24 citations
436. An Annotated Dataset for Explainable Interpersonal Risk Factors of Mental Disturbance in Social Media PostsFindings24 citations
437. Attributable and Scalable Opinion SummarizationLong24 citations
438. CAME: Confidence-guided Adaptive Memory Efficient OptimizationLong24 citations
439. Defending against Insertion-based Textual Backdoor Attacks via AttributionFindings24 citations
440. Downstream Datasets Make Surprisingly Good Pretraining CorporaLong24 citations
441. Enhancing Dialogue Generation via Dynamic Graph Knowledge AggregationLong24 citations
442. Evaluating Embedding APIs for Information RetrievalIndustry24 citations
443. FEDLEGAL: The First Real-World Federated Learning Benchmark for Legal NLPLong24 citations
444. GENEVA: Benchmarking Generalizability for Event Argument Extraction with Hundreds of Event Types and Argument RolesLong24 citations
445. GreenKGC: A Lightweight Knowledge Graph Completion MethodLong24 citations
446. Hybrid Uncertainty Quantification for Selective Text Classification in Ambiguous TasksLong24 citations
447. InfoMetIC: An Informative Metric for Reference-free Image Caption EvaluationLong24 citations
448. Language Models for German Text Simplification: Overcoming Parallel Data Scarcity through Style-specific Pre-trainingFindings24 citations
449. Mind the Biases: Quantifying Cognitive Biases in Language Model PromptingFindings24 citations
450. Multimodal Relation Extraction with Cross-Modal Retrieval and SynthesisShort24 citations
451. Naamapadam: A Large-Scale Named Entity Annotated Data for Indic LanguagesLong24 citations
452. Non-Repeatable Experiments and Non-Reproducible Results: The Reproducibility Crisis in Human Evaluation in NLPFindings24 citations
453. PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional ExpertsLong24 citations
454. Rogue ScoresLong24 citations
455. Semantic Structure Enhanced Event Causality IdentificationLong24 citations
456. Shrinking Embeddings for Hyper-Relational Knowledge GraphsLong24 citations
457. TeAST: Temporal Knowledge Graph Embedding via Archimedean Spiral TimelineLong24 citations
458. The Ecological Fallacy in Annotation: Modeling Human Label Variation goes beyond SociodemographicsShort24 citations
459. The Tail Wagging the Dog: Dataset Construction Biases of Social Bias BenchmarksShort24 citations
460. Transforming Visual Scene Graphs to Image CaptionsLong24 citations
461. WACO: Word-Aligned Contrastive Learning for Speech TranslationLong24 citations
462. What’s the Meaning of Superhuman Performance in Today’s NLU?Long24 citations
463. A Comparative Study on the Impact of Model Compression Techniques on Fairness in Language ModelsLong23 citations
464. Aerial Vision-and-Dialog NavigationFindings23 citations
465. Attention as a Guide for Simultaneous Speech TranslationLong23 citations
466. Counterspeeches up my sleeve! Intent Distribution Learning and Persistent Fusion for Intent-Conditioned Counterspeech GenerationLong23 citations
467. Don’t Forget Your ABC’s: Evaluating the State-of-the-Art in Chat-Oriented Dialogue SystemsLong23 citations
468. Enhancing Hierarchical Text Classification through Knowledge Graph IntegrationFindings23 citations
469. Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting ModelLong23 citations
470. From Dogwhistles to Bullhorns: Unveiling Coded Rhetoric with Language ModelsLong23 citations
471. GanLM: Encoder-Decoder Pre-training with an Auxiliary DiscriminatorLong23 citations
472. LMCap: Few-shot Multilingual Image Captioning by Retrieval Augmented Language Model PromptingFindings23 citations
473. Language Model Analysis for Ontology Subsumption InferenceFindings23 citations
474. Nonparametric Decoding for Generative RetrievalFindings23 citations
475. OD-RTE: A One-Stage Object Detection Framework for Relational Triple ExtractionLong23 citations
476. One Network, Many Masks: Towards More Parameter-Efficient Transfer LearningLong23 citations
477. PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment RecognitionFindings23 citations
478. ReAugKD: Retrieval-Augmented Knowledge Distillation For Pre-trained Language ModelsShort23 citations
479. Recursion of Thought: A Divide-and-Conquer Approach to Multi-Context Reasoning with Language ModelsFindings23 citations
480. Rethinking Multimodal Entity and Relation Extraction from a Translation Point of ViewLong23 citations
481. Robustness of Learning from Task InstructionsFindings23 citations
482. Token-Level Self-Evolution Training for Sequence-to-Sequence LearningShort23 citations
483. Weaker Than You Think: A Critical Look at Weakly Supervised LearningLong23 citations
484. What about “em”? How Commercial Machine Translation Fails to Handle (Neo-)PronounsLong23 citations
485. What does a Text Classifier Learn about Morality? An Explainable Method for Cross-Domain Comparison of Moral RhetoricLong23 citations
486. A Multi-dimensional study on Bias in Vision-Language modelsFindings22 citations
487. Client-Customized Adaptation for Parameter-Efficient Federated LearningFindings22 citations
488. Contextualized Soft Prompts for Extraction of Event ArgumentsFindings22 citations
489. Counterfactual reasoning: Testing language models’ understanding of hypothetical scenariosShort22 citations
490. Cross-Domain Data Augmentation with Domain-Adaptive Language Modeling for Aspect-Based Sentiment AnalysisLong22 citations
491. Dealing with Semantic Underspecification in Multimodal NLPLong22 citations
492. Dialogue Planning via Brownian Bridge Stochastic Process for Goal-directed Proactive DialogueFindings22 citations
493. Diverse Retrieval-Augmented In-Context Learning for Dialogue State TrackingFindings22 citations
494. Dynamic Heterogeneous-Graph Reasoning with Language Models and Knowledge Representation Learning for Commonsense Question AnsweringLong22 citations
495. End-to-end Knowledge Retrieval with Multi-modal QueriesLong22 citations
496. FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph ParsingFindings22 citations
497. Few-shot Joint Multimodal Aspect-Sentiment Analysis Based on Generative Multimodal PromptFindings22 citations
498. How to Plant Trees in Language Models: Data and Architectural Effects on the Emergence of Syntactic Inductive BiasesLong22 citations
499. Improving Grammatical Error Correction with Multimodal Feature IntegrationFindings22 citations
500. Improving Self-training for Cross-lingual Named Entity Recognition with Contrastive and Prototype LearningLong22 citations
501. LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document UnderstandingLong22 citations
502. OASum: Large-Scale Open Domain Aspect-based SummarizationFindings22 citations
503. OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality AlignmentLong22 citations
504. Optimal Transport for Unsupervised Hallucination Detection in Neural Machine TranslationLong22 citations
505. Overcoming Catastrophic Forgetting in Massively Multilingual Continual LearningFindings22 citations
506. Peek Across: Improving Multi-Document Modeling via Cross-Document Question-AnsweringLong22 citations
507. Ranking-Enhanced Unsupervised Sentence Representation LearningLong22 citations
508. Speech-to-Speech Translation for a Real-world Unwritten LanguageFindings22 citations
509. TextObfuscator: Making Pre-trained Language Model a Privacy Protector via Obfuscating Word RepresentationsFindings22 citations
510. Understanding Client Reactions in Online Mental Health CounselingLong22 citations
511. UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive LearningFindings22 citations
512. UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot SummarizationLong22 citations
513. Zero-Shot and Few-Shot Stance Detection on Varied Topics via Conditional GenerationShort22 citations
514. A Gradient Control Method for Backdoor Attacks on Parameter-Efficient TuningLong21 citations
515. AD-KD: Attribution-Driven Knowledge Distillation for Language Model CompressionLong21 citations
516. An Investigation of Evaluation Methods in Automatic Medical Note GenerationFindings21 citations
517. Automated Metrics for Medical Multi-Document Summarization Disagree with Human EvaluationsLong21 citations
518. BLASER: A Text-Free Speech-to-Speech Translation Evaluation MetricLong21 citations
519. CLAPSpeech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-TrainingLong21 citations
520. Causes and Cures for Interference in Multilingual TranslationLong21 citations
521. Context or Knowledge is Not Always Necessary: A Contrastive Learning Framework for Emotion Recognition in ConversationsFindings21 citations
522. Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-rankerFindings21 citations
523. Double-Branch Multi-Attention based Graph Neural Network for Knowledge Graph CompletionLong21 citations
524. FIREBALL: A Dataset of Dungeons and Dragons Actual-Play with Structured Game State InformationLong21 citations
525. FolkScope: Intention Knowledge Graph Construction for E-commerce Commonsense DiscoveryFindings21 citations
526. GDA: Generative Data Augmentation Techniques for Relation Extraction TasksFindings21 citations
527. Learning by Analogy: Diverse Questions Generation in Math Word ProblemFindings21 citations
528. MVP-Tuning: Multi-View Knowledge Retrieval with Prompt Tuning for Commonsense ReasoningLong21 citations
529. Multi3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented DialogueFindings21 citations
530. On Evaluating and Mitigating Gender Biases in Multilingual SettingsFindings21 citations
531. ParaLS: Lexical Substitution via Pretrained ParaphraserLong21 citations
532. PeaCoK: Persona Commonsense Knowledge for Consistent and Engaging NarrativesLong21 citations
533. Playing the Part of the Sharp Bully: Generating Adversarial Examples for Implicit Hate Speech DetectionFindings21 citations
534. Plug-and-Play Knowledge Injection for Pre-trained Language ModelsLong21 citations
535. RMSSinger: Realistic-Music-Score based Singing Voice SynthesisFindings21 citations
536. Rethinking Semi-supervised Learning with Language ModelsFindings21 citations
537. RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language ModelsLong21 citations
538. Reward Gaming in Conditional Text GenerationLong21 citations
539. Span-level Aspect-based Sentiment Analysis via Table FillingLong21 citations
540. Teaching the Pre-trained Model to Generate Simple Texts for Text SimplificationFindings21 citations
541. Text Adversarial Purification as Defense against Adversarial AttacksLong21 citations
542. The Benefits of Bad Advice: Autocontrastive Decoding across Model LayersLong21 citations
543. Automatic Table Union Search with Tabular Representation LearningFindings20 citations
544. CREPE: Open-Domain Question Answering with False PresuppositionsLong20 citations
545. CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive SummarizationFindings20 citations
546. Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction?Long20 citations
547. Conformal Nucleus SamplingFindings20 citations
548. Cost-effective Distillation of Large Language ModelsFindings20 citations
549. Counterfactual Active Learning for Out-of-Distribution GeneralizationLong20 citations
550. Dataset Distillation with Attention Labels for Fine-tuning BERTShort20 citations
551. Dialect-robust Evaluation of Generated TextLong20 citations
552. DiffusEmp: A Diffusion Model-Based Framework with Multi-Grained Control for Empathetic Response GenerationLong20 citations
553. Disentangled Phonetic Representation for Chinese Spelling CorrectionLong20 citations
554. Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question AnsweringFindings20 citations
555. Frustratingly Easy Label Projection for Cross-lingual TransferFindings20 citations
556. Generative Zero-Shot Prompt Learning for Cross-Domain Slot Filling with Inverse PromptingFindings20 citations
557. Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency RegularizationFindings20 citations
558. IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation Metrics for Indian LanguagesLong20 citations
559. LiveChat: A Large-Scale Personalized Dialogue Dataset Automatically Constructed from Live StreamingLong20 citations
560. Log-linear Guardedness and its ImplicationsLong20 citations
561. Measuring Progress in Fine-grained Vision-and-Language UnderstandingLong20 citations
562. Modular and On-demand Bias Mitigation with Attribute-Removal SubnetworksFindings20 citations
563. MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral DiscussionsLong20 citations
564. More than Classification: A Unified Framework for Event Temporal Relation ExtractionLong20 citations
565. Multi-source Semantic Graph-based Multimodal Sarcasm Explanation GenerationLong20 citations
566. Open-ended Long Text Generation via Masked Language ModelingLong20 citations
567. PREADD: Prefix-Adaptive Decoding for Controlled Text GenerationFindings20 citations
568. Socratic Pretraining: Question-Driven Pretraining for Controllable SummarizationLong20 citations
569. Speech-Text Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal AlignmentLong20 citations
570. Targeted Data Generation: Finding and Fixing Model WeaknessesLong20 citations
571. Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuningShort20 citations
572. Towards Imperceptible Document Manipulations against Neural Ranking ModelsFindings20 citations
573. Towards standardizing Korean Grammatical Error Correction: Datasets and AnnotationLong20 citations
574. Training Models to Generate, Recognize, and Reframe Unhelpful ThoughtsLong20 citations
575. Trigger Warning Assignment as a Multi-Label Document Classification ProblemLong20 citations
576. Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global TransportFindings20 citations
577. What Makes Pre-trained Language Models Better Zero-shot Learners?Long20 citations
578. pNLP-Mixer: an Efficient all-MLP Architecture for LanguageIndustry20 citations
579. BOLT: Fast Energy-based Controlled Text Generation with Tunable BiasesShort19 citations
580. Beyond English-Centric Bitexts for Better Multilingual Language Representation LearningLong19 citations
581. Bidirectional Generative Framework for Cross-domain Aspect-based Sentiment AnalysisLong19 citations
582. CHEER: Centrality-aware High-order Event Reasoning Network for Document-level Event Causality IdentificationLong19 citations
583. DEplain: A German Parallel Corpus with Intralingual Translations into Plain Language for Sentence and Document SimplificationLong19 citations
584. Deeply Coupled Cross-Modal Prompt LearningFindings19 citations
585. Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State TrackingLong19 citations
586. ESCOXLM-R: Multilingual Taxonomy-driven Pre-training for the Job Market DomainLong19 citations
587. Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text TasksLong19 citations
588. Linear Classifier: An Often-Forgotten Baseline for Text ClassificationShort19 citations
589. MANNER: A Variational Memory-Augmented Model for Cross Domain Few-Shot Named Entity RecognitionLong19 citations
590. Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation ModelLong19 citations
591. MetaVL: Transferring In-Context Learning Ability From Language Models to Vision-Language ModelsShort19 citations
592. Metaphor Detection via Explicit Basic Meanings ModellingShort19 citations
593. Movie101: A New Movie Understanding BenchmarkLong19 citations
594. PEIT: Bridging the Modality Gap with Pre-trained Models for End-to-End Image TranslationLong19 citations
595. Prompt to be Consistent is Better than Self-Consistent? Few-Shot and Zero-Shot Fact Verification with Pre-trained Language ModelsFindings19 citations
596. RFiD: Towards Rational Fusion-in-Decoder for Open-Domain Question AnsweringFindings19 citations
597. SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created through Human-Machine CollaborationLong19 citations
598. STT4SG-350: A Speech Corpus for All Swiss German Dialect RegionsShort19 citations
599. Search-Oriented Conversational Query EditingFindings19 citations
600. The Devil is in the Details: On the Pitfalls of Event Extraction EvaluationFindings19 citations
601. The Magic of IF: Investigating Causal Reasoning Abilities in Large Language Models of CodeFindings19 citations
602. Tree-Based Representation and Generation of Natural and Mathematical LanguageLong19 citations
603. Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad PredictionFindings19 citations
604. Understanding Programs by Exploiting (Fuzzing) Test CasesFindings19 citations
605. UniCoRN: Unified Cognitive Signal ReconstructioN bridging cognitive signals and human languageLong19 citations
606. What Is Overlap Knowledge in Event Argument Extraction? APE: A Cross-datasets Transfer Learning Model for EAELong19 citations
607. WikiHowQA: A Comprehensive Benchmark for Multi-Document Non-Factoid Question AnsweringLong19 citations
608. A Diverse Set of Freely Available Linguistic Resources for TurkishLong18 citations
609. A Static Evaluation of Code Completion by Large Language ModelsIndustry18 citations
610. AV-TranSpeech: Audio-Visual Robust Speech-to-Speech TranslationLong18 citations
611. BanglaBook: A Large-scale Bangla Dataset for Sentiment Analysis from Book ReviewsFindings18 citations
612. C-STANCE: A Large Dataset for Chinese Zero-Shot Stance DetectionLong18 citations
613. CFSum Coarse-to-Fine Contribution Network for Multimodal SummarizationLong18 citations
614. Claim-Dissector: An Interpretable Fact-Checking System with Joint Re-ranking and Veracity PredictionFindings18 citations
615. Controllable Text Generation via Probability Density Estimation in the Latent SpaceLong18 citations
616. DIP: Dead code Insertion based Black-box Attack for Programming Language ModelLong18 citations
617. Data-Efficient Finetuning Using Cross-Task Nearest NeighborsFindings18 citations
618. Discriminative Reasoning with Sparse Event Representation for Document-level Event-Event Relation ExtractionLong18 citations
619. Enhancing Grammatical Error Correction Systems with ExplanationsLong18 citations
620. Entity-to-Text based Data Augmentation for various Named Entity Recognition TasksFindings18 citations
621. Evaluating Open-Domain Dialogues in Latent Space with Next Sentence Prediction and Mutual InformationLong18 citations
622. From Alignment to Entailment: A Unified Textual Entailment Framework for Entity AlignmentFindings18 citations
623. Generating Structured Pseudo Labels for Noise-resistant Zero-shot Video Sentence LocalizationLong18 citations
624. Generic Temporal Reasoning with Differential Analysis and ExplanationLong18 citations
625. Global and Local Hierarchy-aware Contrastive Framework for Implicit Discourse Relation RecognitionFindings18 citations
626. Joint Document-Level Event Extraction via Token-Token Bidirectional Event Completed GraphLong18 citations
627. Layer-wise Fusion with Modality Independence Modeling for Multi-modal Emotion RecognitionLong18 citations
628. Learning to Simulate Natural Language Feedback for Interactive Semantic ParsingLong18 citations
629. Lego-MT: Learning Detachable Models for Massively Multilingual Machine TranslationFindings18 citations
630. MGR: Multi-generator Based RationalizationLong18 citations
631. MUSTIE: Multimodal Structural Transformer for Web Information ExtractionLong18 citations
632. MultiTabQA: Generating Tabular Answers for Multi-Table Question AnsweringLong18 citations
633. On the Difference of BERT-style and CLIP-style Text EncodersFindings18 citations
634. Open-WikiTable : Dataset for Open Domain Question Answering with Complex Reasoning over TableFindings18 citations
635. Prefix Propagation: Parameter-Efficient Tuning for Long SequencesShort18 citations
636. Randomized Smoothing with Masked Inference for Adversarially Robust Text ClassificationsLong18 citations
637. Rule By Example: Harnessing Logical Rules for Explainable Hate Speech DetectionLong18 citations
638. Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based ProjectionFindings18 citations
639. Subset Retrieval Nearest Neighbor Machine TranslationLong18 citations
640. Unified Language Representation for Question Answering over Text, Tables, and ImagesFindings18 citations
641. miCSE: Mutual Information Contrastive Learning for Low-shot Sentence EmbeddingsLong18 citations
642. ACLM: A Selective-Denoising based Generative Data Augmentation Approach for Low-Resource Complex NERLong17 citations
643. Abductive Commonsense Reasoning Exploiting Mutually Exclusive ExplanationsLong17 citations
644. Annotation-Inspired Implicit Discourse Relation Classification with Auxiliary Discourse Connective GenerationLong17 citations
645. COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference PerspectiveLong17 citations
646. CREST: A Joint Framework for Rationalization and Counterfactual Text GenerationLong17 citations
647. Causality-Guided Multi-Memory Interaction Network for Multivariate Stock Price Movement PredictionLong17 citations
648. Check-COVID: Fact-Checking COVID-19 News Claims with Scientific EvidenceFindings17 citations
649. CodePrompt: Task-Agnostic Prefix Tuning for Program and Language GenerationFindings17 citations
650. Combo of Thinking and Observing for Outside-Knowledge VQALong17 citations
651. DataFinder: Scientific Dataset Recommendation from Natural Language DescriptionsLong17 citations
652. Document-Level Event Argument Extraction With a Chain Reasoning ParadigmLong17 citations
653. Dual-Gated Fusion with Prefix-Tuning for Multi-Modal Relation ExtractionFindings17 citations
654. EM Pre-training for Multi-party Dialogue Response GenerationLong17 citations
655. Few-shot Reranking for Multi-hop QA via Language Model PromptingLong17 citations
656. FluentSpeech: Stutter-Oriented Automatic Speech Editing with Context-Aware Diffusion ModelsFindings17 citations
657. Generate then Select: Open-ended Visual Question Answering Guided by World KnowledgeFindings17 citations
658. How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacksLong17 citations
659. HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language TasksFindings17 citations
660. Interactive Concept Learning for Uncovering Latent Themes in Large Text CollectionsFindings17 citations
661. Language model acceptability judgements are not always robust to contextLong17 citations
662. Leveraging Training Data in Few-Shot Prompting for Numerical ReasoningFindings17 citations
663. Mini-Model Adaptation: Efficiently Extending Pretrained Models to New Languages via Aligned Shallow TrainingFindings17 citations
664. PESCO: Prompt-enhanced Self Contrastive Learning for Zero-shot Text ClassificationLong17 citations
665. Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive TasksFindings17 citations
666. QUEST: A Retrieval Dataset of Entity-Seeking Queries with Implicit Set OperationsLong17 citations
667. RHGN: Relation-gated Heterogeneous Graph Network for Entity Alignment in Knowledge GraphsFindings17 citations
668. Recurrent Attention Networks for Long-text ModelingFindings17 citations
669. Revisiting Token Dropping Strategy in Efficient BERT PretrainingLong17 citations
670. TAVT: Towards Transferable Audio-Visual Text GenerationLong17 citations
671. Text Style Transfer Back-TranslationLong17 citations
672. Toward Expanding the Scope of Radiology Report Summarization to Multiple Anatomies and ModalitiesShort17 citations
673. Two Heads Are Better Than One: Improving Fake News Video Detection by Correlating with NeighborsFindings17 citations
674. Unsupervised Melody-to-Lyrics GenerationLong17 citations
675. VLN-Trans: Translator for the Vision and Language Navigation AgentLong17 citations
676. Werewolf Among Us: Multimodal Resources for Modeling Persuasion Behaviors in Social Deduction GamesFindings17 citations
677. A Novel Table-to-Graph Generation Approach for Document-Level Joint Entity and Relation ExtractionLong16 citations
678. A Probabilistic Framework for Discovering New IntentsLong16 citations
679. A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target TrainingLong16 citations
680. A Unified One-Step Solution for Aspect Sentiment Quad PredictionFindings16 citations
681. Alleviating Over-smoothing for Unsupervised Sentence RepresentationLong16 citations
682. Are Human Explanations Always Helpful? Towards Objective Evaluation of Human Natural Language ExplanationsLong16 citations
683. Are Message Passing Neural Networks Really Helpful for Knowledge Graph Completion?Long16 citations
684. AutoConv: Automatically Generating Information-seeking Conversations with Large Language ModelsShort16 citations
685. BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk TrainingLong16 citations
686. Bias Beyond English: Counterfactual Tests for Bias in Sentiment Analysis in Four LanguagesFindings16 citations
687. Boosting Distress Support Dialogue Responses with Motivational Interviewing StrategyFindings16 citations
688. Class-Incremental Learning based on Label GenerationShort16 citations
689. Composition-contrastive Learning for Sentence EmbeddingsLong16 citations
690. DiSCoMaT: Distantly Supervised Composition Extraction from Tables in Materials Science ArticlesLong16 citations
691. Do You Hear The People Sing? Key Point Analysis via Iterative Clustering and Abstractive SummarisationLong16 citations
692. Exploring Better Text Image Translation with Multimodal CodebookLong16 citations
693. Extrinsic Evaluation of Machine Translation MetricsLong16 citations
694. Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language ModelsLong16 citations
695. Human-in-the-loop Abstractive Dialogue SummarizationFindings16 citations
696. HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation PerturbationLong16 citations
697. Improving Continual Relation Extraction by Distinguishing Analogous SemanticsLong16 citations
698. Improving Knowledge Graph Completion with Generative Hard Negative MiningFindings16 citations
699. Incorporating Distributions of Discourse Structure for Long Document Abstractive SummarizationLong16 citations
700. It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of PerformanceFindings16 citations
701. LightFormer: Light-weight Transformer Using SVD-based Weight Transfer and Parameter SharingFindings16 citations
702. Multi-CLS BERT: An Efficient Alternative to Traditional EnsemblingLong16 citations
703. Multi-hop Evidence Retrieval for Cross-document Relation ExtractionFindings16 citations
704. MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual CaptioningLong16 citations
705. NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference ChecklistLong16 citations
706. On the Off-Target Problem of Zero-Shot Multilingual Neural Machine TranslationFindings16 citations
707. On the Strength of Sequence Labeling and Generative Models for Aspect Sentiment Triplet ExtractionFindings16 citations
708. One Cannot Stand for Everyone! Leveraging Multiple User Simulators to train Task-oriented Dialogue SystemsLong16 citations
709. QAP: A Quantum-Inspired Adaptive-Priority-Learning Model for Multimodal Emotion RecognitionFindings16 citations
710. Reliable and Interpretable Drift Detection in Streams of Short TextsIndustry16 citations
711. TREA: Tree-Structure Reasoning Schema for Conversational RecommendationLong16 citations
712. The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation MetricsShort16 citations
713. The State of Profanity Obfuscation in Natural Language Processing Scientific PublicationsFindings16 citations
714. Unifying Cross-Lingual and Cross-Modal Modeling Towards Weakly Supervised Multilingual Vision-Language Pre-trainingLong16 citations
715. VCSUM: A Versatile Chinese Meeting Summarization DatasetFindings16 citations
716. Where’s the Point? Self-Supervised Multilingual Punctuation-Agnostic Sentence SegmentationLong16 citations
717. Why Does Zero-Shot Cross-Lingual Generation Fail? An Explanation and a SolutionFindings16 citations
718. World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language ModelsLong16 citations
719. Zero- and Few-Shot Event Detection via Prompt-Based Meta LearningLong16 citations
720. A Match Made in Heaven: A Multi-task Framework for Hyperbole and Metaphor DetectionFindings15 citations
721. A Sequence-to-Sequence&Set Model for Text-to-Table GenerationFindings15 citations
722. A Universal Discriminator for Zero-Shot GeneralizationLong15 citations
723. Annotating and Detecting Fine-grained Factual Errors for Dialogue SummarizationLong15 citations
724. Bidirectional Transformer Reranker for Grammatical Error CorrectionFindings15 citations
725. Can Diffusion Model Achieve Better Performance in Text Generation ? Bridging the Gap between Training and Inference !Findings15 citations
726. Causality-aware Concept Extraction based on Knowledge-guided PromptingLong15 citations
727. Coarse-to-fine Few-shot Learning for Named Entity RecognitionFindings15 citations
728. Conflicts, Villains, Resolutions: Towards models of Narrative Media FramingLong15 citations
729. ContraCLM: Contrastive Learning For Causal Language ModelLong15 citations
730. Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editorsFindings15 citations
731. E-NER: Evidential Deep Learning for Trustworthy Named Entity RecognitionFindings15 citations
732. End-to-End Simultaneous Speech Translation with Differentiable SegmentationFindings15 citations
733. Enhancing Continual Relation Extraction via Classifier DecompositionFindings15 citations
734. Faithful Question Answering with Monte-Carlo PlanningLong15 citations
735. HAHE: Hierarchical Attention for Hyper-Relational Knowledge Graphs in Global and Local LevelLong15 citations
736. Improving Factuality of Abstractive Summarization without Sacrificing Summary QualityShort15 citations
737. KALM: Knowledge-Aware Integration of Local, Document, and Global Contexts for Long Document UnderstandingLong15 citations
738. Know What I don’t Know: Handling Ambiguous and Unknown Questions for Text-to-SQLFindings15 citations
739. Large-scale Lifelong Learning of In-context Instructions and How to Tackle ItLong15 citations
740. Learned Adapters Are Better Than Manually Designed AdaptersFindings15 citations
741. Learning Language-Specific Layers for Multilingual Machine TranslationLong15 citations
742. Learning to Generate Equitable Text in Dialogue from Biased Training DataLong15 citations
743. Learning to Imagine: Visually-Augmented Natural Language GenerationLong15 citations
744. Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?Long15 citations
745. LexSym: Compositionality as Lexical SymmetryLong15 citations
746. Modeling Cross-Cultural Pragmatic Inference with Codenames DuetFindings15 citations
747. Multimodal Persona Based Generation of Comic DialogsLong15 citations
748. On the Limitations of Simulating Active LearningFindings15 citations
749. PAL to Lend a Helping Hand: Towards Building an Emotion Adaptive Polite and Empathetic Counseling Conversational AgentLong15 citations
750. PTCSpell: Pre-trained Corrector Based on Character Shape and Pinyin for Chinese Spelling CorrectionFindings15 citations
751. RobustQA: Benchmarking the Robustness of Domain Adaptation for Open-Domain Question AnsweringFindings15 citations
752. S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question AnsweringShort15 citations
753. SIMSUM: Document-level Text Simplification via Simultaneous SummarizationLong15 citations
754. Self-adaptive Context and Modal-interaction Modeling For Multimodal Emotion RecognitionFindings15 citations
755. Serial Contrastive Knowledge Distillation for Continual Few-shot Relation ExtractionFindings15 citations
756. Simple and Effective Unsupervised Speech TranslationLong15 citations
757. TART: Improved Few-shot Text Classification Using Task-Adaptive Reference TransformationLong15 citations
758. Towards Boosting the Open-Domain Chatbot with Human FeedbackLong15 citations
759. TransGEC: Improving Grammatical Error Correction with TranslationeseFindings15 citations
760. UTC-IE: A Unified Token-pair Classification Architecture for Information ExtractionLong15 citations
761. Won’t Get Fooled Again: Answering Questions with False PremisesLong15 citations
762. Zero-Shot Text Classification via Self-Supervised TuningFindings15 citations
763. 2*n is better than n2: Decomposing Event Coreference Resolution into Two Tractable ProblemsFindings14 citations
764. A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual CluesLong14 citations
765. A New Direction in Stance Detection: Target-Stance Extraction in the WildLong14 citations
766. An (unhelpful) guide to selecting the best ASR architecture for your under-resourced languageShort14 citations
767. Are Experts Needed? On Human Evaluation of Counselling Reflection GenerationLong14 citations
768. BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense RetrievalLong14 citations
769. Characterization of Stigmatizing Language in Medical RecordsShort14 citations
770. Continual Knowledge Distillation for Neural Machine TranslationLong14 citations
771. DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language ModelsLong14 citations
772. Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance MinimizationLong14 citations
773. Fine-grained Artificial Neurons in Audio-transformers for Disentangling Neural Auditory EncodingFindings14 citations
774. Forgotten Knowledge: Examining the Citational Amnesia in NLPLong14 citations
775. Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT OperatorFindings14 citations
776. From Key Points to Key Point Hierarchy: Structured and Expressive Opinion SummarizationLong14 citations
777. Generating User-Engaging News HeadlinesLong14 citations
778. Guide the Many-to-One Assignment: Open Information Extraction via IoU-aware Optimal TransportLong14 citations
779. Improving Domain Generalization for Prompt-Aware Essay Scoring via Disentangled Representation LearningLong14 citations
780. Improving Embedding-based Unsupervised Keyphrase Extraction by Incorporating Structural InformationFindings14 citations
781. Improving the Robustness of Summarization Systems with Dual AugmentationLong14 citations
782. Label-Aware Hyperbolic Embeddings for Fine-grained Emotion ClassificationLong14 citations
783. Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional EmbeddingsShort14 citations
784. Learning Better Masking for Better Language Model Pre-trainingLong14 citations
785. Learning Joint Structural and Temporal Contextualized Knowledge Embeddings for Temporal Knowledge Graph CompletionFindings14 citations
786. Learning Multi-Step Reasoning by Solving Arithmetic TasksShort14 citations
787. Learning from a Friend: Improving Event Extraction via Self-Training with Feedback from Abstract Meaning RepresentationFindings14 citations
788. Local Interpretation of Transformer Based on Linear DecompositionLong14 citations
789. MIL-Decoding: Detoxifying Language Models at Token-Level via Multiple Instance LearningLong14 citations
790. MS-DETR: Natural Language Video Localization with Sampling Moment-Moment InteractionLong14 citations
791. Measuring Your ASTE Models in The Wild: A Diversified Multi-domain Dataset For Aspect Sentiment Triplet ExtractionFindings14 citations
792. Modeling What-to-ask and How-to-ask for Answer-unaware Conversational Question GenerationLong14 citations
793. NaSGEC: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker TextsFindings14 citations
794. NoisywikiHow: A Benchmark for Learning with Real-world Noisy Labels in Natural Language ProcessingFindings14 citations
795. NonFactS: NonFactual Summary Generation for Factuality Evaluation in Document SummarizationFindings14 citations
796. Opinion Tree Parsing for Aspect-based Sentiment AnalysisFindings14 citations
797. PAD-Net: An Efficient Framework for Dynamic NetworksLong14 citations
798. ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-TranslationLong14 citations
799. Personality Understanding of Fictional Characters during Book ReadingLong14 citations
800. Pre-Trained Language-Meaning Models for Multilingual Parsing and GenerationFindings14 citations
801. Preserving Commonsense Knowledge from Pre-trained Language Models via Causal InferenceLong14 citations
802. Privacy-Preserving Domain Adaptation of Semantic ParsersLong14 citations
803. Program Chairs’ Report on Peer Review at ACL 2023Long14 citations
804. Rethinking Document-Level Relation Extraction: A Reality CheckFindings14 citations
805. Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-trainingFindings14 citations
806. Robust Natural Language Understanding with Residual Attention DebiasingFindings14 citations
807. SWiPE: A Dataset for Document-Level Simplification of Wikipedia PagesLong14 citations
808. SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluationLong14 citations
809. Small Pre-trained Language Models Can be Fine-tuned as Large Models via Over-ParameterizationLong14 citations
810. Text-to-SQL Error Correction with Language Models of CodeShort14 citations
811. Topic-Guided Sampling For Data-Efficient Multi-Domain Stance DetectionLong14 citations
812. Towards Faithful Dialogues via Focus LearningLong14 citations
813. Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation RegularizationFindings14 citations
814. TwistList: Resources and Baselines for Tongue Twister GenerationShort14 citations
815. What to Fuse and How to Fuse: Exploring Emotion and Personality Fusion Strategies for Explainable Mental Disorder DetectionFindings14 citations
816. White-Box Multi-Objective Adversarial Attack on Dialogue GenerationLong14 citations
817. Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQALong14 citations
818. A New Aligned Simple German CorpusLong13 citations
819. B2T Connection: Serving Stability and Performance in Deep TransformersFindings13 citations
820. Benchmarking Diverse-Modal Entity Linking with Generative ModelsFindings13 citations
821. Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language ModelsFindings13 citations
822. COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLPFindings13 citations
823. Communication Efficient Federated Learning for Multilingual Neural Machine Translation with AdapterFindings13 citations
824. Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge GraphsFindings13 citations
825. Connective Prediction for Implicit Discourse Relation Recognition via Knowledge DistillationLong13 citations
826. Contrastive Error Attribution for Finetuned Language ModelsLong13 citations
827. Cross-modal Attention Congruence Regularization for Vision-Language Relation AlignmentLong13 citations
828. Deep Span Representations for Named Entity RecognitionFindings13 citations
829. Deriving Language Models from Masked Language ModelsShort13 citations
830. Do language models have coherent mental models of everyday things?Long13 citations
831. Dual-Alignment Pre-training for Cross-lingual Sentence EmbeddingLong13 citations
832. Efficient Out-of-Domain Detection for Sequence to Sequence ModelsFindings13 citations
833. Enhancing Event Causality Identification with Counterfactual ReasoningShort13 citations
834. Exploiting Pseudo Image Captions for Multimodal SummarizationFindings13 citations
835. Exploring the Relationship between Alignment and Cross-lingual Transfer in Multilingual TransformersFindings13 citations
836. FSUIE: A Novel Fuzzy Span Mechanism for Universal Information ExtractionLong13 citations
837. Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and BenchmarksLong13 citations
838. FastDiff 2: Revisiting and Incorporating GANs and Diffusion Models in High-Fidelity Speech SynthesisFindings13 citations
839. GKD: A General Knowledge Distillation Framework for Large-scale Pre-trained Language ModelIndustry13 citations
840. Grounding Characters and Places in Narrative TextLong13 citations
841. Hybrid Hierarchical Retrieval for Open-Domain Question AnsweringFindings13 citations
842. Hybrid Knowledge Transfer for Improved Cross-Lingual Event Detection via Hierarchical Sample SelectionLong13 citations
843. HyperMixer: An MLP-based Low Cost Alternative to TransformersLong13 citations
844. Interpretable Automatic Fine-grained Inconsistency Detection in Text SummarizationFindings13 citations
845. Just Like a Human Would, Direct Access to Sarcasm Augmented with Potential Result and ReactionLong13 citations
846. Knowledge Transfer in Incremental Learning for Multilingual Neural Machine TranslationLong13 citations
847. Large-Scale Correlation Analysis of Automated Metrics for Topic ModelsLong13 citations
848. Learning Optimal Policy for Simultaneous Machine Translation via Binary SearchLong13 citations
849. MIR-GAN: Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech RecognitionLong13 citations
850. Multi-Dimensional Evaluation of Text Summarization with In-Context LearningFindings13 citations
851. Multi-Document Summarization with Centroid-Based PretrainingShort13 citations
852. Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented DialogLong13 citations
853. Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QALong13 citations
854. Product Question Answering in E-Commerce: A SurveyLong13 citations
855. Rarely a problem? Language models exhibit inverse scaling in their predictions following few-type quantifiersFindings13 citations
856. Replace and Report: NLP Assisted Radiology Report GenerationFindings13 citations
857. Robust Representation Learning with Reliable Pseudo-labels Generation via Self-Adaptive Optimal Transport for Short Text ClusteringLong13 citations
858. Similarity-Based Content Scoring - A more Classroom-Suitable Alternative to Instance-Based Scoring?Findings13 citations
859. Translation-Enhanced Multilingual Text-to-Image GenerationLong13 citations
860. Unbalanced Optimal Transport for Unbalanced Word AlignmentLong13 citations
861. UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive PerspectiveLong13 citations
862. Why Aren’t We NER Yet? Artifacts of ASR Errors in Named Entity Recognition in Spontaneous Speech TranscriptsLong13 citations
863. Words as Gatekeepers: Measuring Discipline-specific Terms and Meanings in Scholarly PublicationsFindings13 citations
864. vONTSS: vMF based semi-supervised neural topic modeling with optimal transportFindings13 citations
865. A Unified Generative Approach to Product Attribute-Value IdentificationFindings12 citations
866. ALERT: Adapt Language Models to Reasoning TasksLong12 citations
867. An Empirical Study of Sentiment-Enhanced Pre-Training for Aspect-Based Sentiment AnalysisFindings12 citations
868. AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language ProcessingFindings12 citations
869. Are Fairy Tales Fair? Analyzing Gender Bias in Temporal Narrative Event Chains of Children’s Fairy TalesLong12 citations
870. ArgU: A Controllable Factual Argument GeneratorLong12 citations
871. Back Translation for Speech-to-text Translation Without TranscriptsLong12 citations
872. Better Simultaneous Translation with Monotonic Knowledge DistillationLong12 citations
873. Beyond Triplet: Leveraging the Most Data for Multimodal Machine TranslationFindings12 citations
874. Bhasa-Abhijnaanam: Native-script and romanized Language Identification for 22 Indic languagesShort12 citations
875. Context-Aware Document SimplificationFindings12 citations
876. DSP: Discriminative Soft Prompts for Zero-Shot Entity and Relation ExtractionFindings12 citations
877. Delving into the Openness of CLIPFindings12 citations
878. Denoising Bottleneck with Mutual Information Maximization for Video Multimodal FusionLong12 citations
879. Do CoNLL-2003 Named Entity Taggers Still Work Well in 2023?Long12 citations
880. End-to-end Aspect-based Sentiment Analysis with Combinatory Categorial GrammarFindings12 citations
881. Estimating the Uncertainty in Emotion Attributes using Deep Evidential RegressionLong12 citations
882. Explanation-based Finetuning Makes Models More Robust to Spurious CuesLong12 citations
883. FLamE: Few-shot Learning from Natural Language ExplanationsLong12 citations
884. FashionKLIP: Enhancing E-Commerce Image-Text Retrieval with Fashion Multi-Modal Conceptual Knowledge GraphIndustry12 citations
885. Few-Shot Document-Level Event Argument ExtractionLong12 citations
886. FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information ExtractionLong12 citations
887. Going Beyond Sentence Embeddings: A Token-Level Matching Algorithm for Calculating Semantic Textual SimilarityShort12 citations
888. Human-in-the-loop Evaluation for Early Misinformation Detection: A Case Study of COVID-19 TreatmentsLong12 citations
889. Improved Visual Story Generation with Adaptive Context ModelingFindings12 citations
890. Incorporating Graph Information in Transformer-based AMR ParsingFindings12 citations
891. Infusing Hierarchical Guidance into Prompt Tuning: A Parameter-Efficient Framework for Multi-level Implicit Discourse Relation RecognitionLong12 citations
892. Interpretable Math Word Problem Solution Generation via Step-by-step PlanningLong12 citations
893. Language Agnostic Multilingual Information Retrieval with Contrastive LearningFindings12 citations
894. Learn to Not Link: Exploring NIL Prediction in Entity LinkingFindings12 citations
895. Linguistic representations for fewer-shot relation extraction across domainsLong12 citations
896. Making Better Use of Training Corpus: Retrieval-based Aspect Sentiment Triplet Extraction via Label InterpolationFindings12 citations
897. MidMed: Towards Mixed-Type Dialogues for Medical ConsultationLong12 citations
898. MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-EntropiesLong12 citations
899. Multi-modal Action Chain Abductive ReasoningLong12 citations
900. Multilingual Conceptual Coverage in Text-to-Image ModelsLong12 citations
901. Multilingual Multi-Figurative Language DetectionFindings12 citations
902. Nichelle and Nancy: The Influence of Demographic Attributes and Tokenization Length on First Name BiasesShort12 citations
903. Nonlinear Structural Equation Model Guided Gaussian Mixture Hierarchical Topic ModelingLong12 citations
904. Pay Attention to Implicit Attribute Values: A Multi-modal Generative Framework for AVE TaskFindings12 citations
905. Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social BiasesLong12 citations
906. Reproducibility in NLP: What Have We Learned from the Checklist?Findings12 citations
907. Resolving Ambiguities in Text-to-Image Generative ModelsLong12 citations
908. Run Like a Girl! Sport-Related Gender Bias in Language and VisionFindings12 citations
909. ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context LearningShort12 citations
910. Speaking the Language of Your Listener: Audience-Aware Adaptation via Plug-and-Play Theory of MindFindings12 citations
911. Structured Persuasive Writing Support in Legal Education: A Model and Tool for German Legal Case SolutionsFindings12 citations
912. Tell2Design: A Dataset for Language-Guided Floor Plan GenerationLong12 citations
913. Towards Building a Robust Toxicity PredictorIndustry12 citations
914. Towards Parameter-Efficient Integration of Pre-Trained Language Models In Temporal Video GroundingFindings12 citations
915. Two Birds One Stone: Dynamic Ensemble for OOD Intent ClassificationLong12 citations
916. Uncertainty Guided Label Denoising for Document-level Distant Relation ExtractionLong12 citations
917. Unsupervised Semantic Variation Prediction using the Distribution of Sibling EmbeddingsFindings12 citations
918. Unsupervised Task Graph Generation from Instructional Video TranscriptsFindings12 citations
919. Vision Language Pre-training by Contrastive Learning with Cross-Modal Similarity RegulationLong12 citations
920. WebIE: Faithful and Robust Information Extraction on the WebLong12 citations
921. What, When, and How to Ground: Designing User Persona-Aware Conversational Agents for Engaging DialogueIndustry12 citations
922. Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document UnderstandingLong12 citations
923. Zero-shot Visual Question Answering with Language Model FeedbackFindings12 citations
924. kNN-TL: k-Nearest-Neighbor Transfer Learning for Low-Resource Neural Machine TranslationLong12 citations
925. A Call for Standardization and Validation of Text Style Transfer EvaluationFindings11 citations
926. A Needle in a Haystack: An Analysis of High-Agreement Workers on MTurk for SummarizationLong11 citations
927. A Simple and Effective Framework for Strict Zero-Shot Hierarchical ClassificationShort11 citations
928. Aligning Offline Metrics and Human Judgments of Value for Code Generation ModelsFindings11 citations
929. An Extensible Plug-and-Play Method for Multi-Aspect Controllable Text GenerationLong11 citations
930. An Inner Table Retriever for Robust Table Question AnsweringLong11 citations
931. Are Synonym Substitution Attacks Really Synonym Substitution Attacks?Findings11 citations
932. Binary and Ternary Natural Language GenerationLong11 citations
933. Compositional Data Augmentation for Abstractive Conversation SummarizationLong11 citations
934. Content Moderation for Evolving Policies using Binary Question AnsweringIndustry11 citations
935. Controlling Styles in Neural Machine Translation with Activation PromptFindings11 citations
936. D-CALM: A Dynamic Clustering-based Active Learning Approach for Mitigating BiasFindings11 citations
937. DIONYSUS: A Pre-trained Model for Low-Resource Dialogue SummarizationLong11 citations
938. Decouple knowledge from paramters for plug-and-play language modelingFindings11 citations
939. Dialogue Summarization with Static-Dynamic Structure Fusion GraphLong11 citations
940. DiffuDetox: A Mixed Diffusion Model for Text DetoxificationFindings11 citations
941. Discourse-Level Representations can Improve Prediction of Degree of AnxietyShort11 citations
942. Elaboration-Generating Commonsense Question Answering at ScaleLong11 citations
943. Enhancing Event Causality Identification with Event Causal Label and Event Pair Interaction GraphFindings11 citations
944. Enhancing Neural Topic Model with Multi-Level Supervisions from Seed WordsFindings11 citations
945. Evaluation for ChangeFindings11 citations
946. Exploring Lottery Prompts for Pre-trained Language ModelsLong11 citations
947. Faithful Low-Resource Data-to-Text Generation through Cycle TrainingLong11 citations
948. Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language ModelFindings11 citations
949. Focus-aware Response Generation in Inquiry ConversationFindings11 citations
950. Forecasting Earnings Surprises from Conference Call TranscriptsFindings11 citations
951. General-to-Specific Transfer Labeling for Domain Adaptable Keyphrase GenerationFindings11 citations
952. Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech RecognitionLong11 citations
953. Improving Long Dialogue Summarization with Semantic Graph RepresentationFindings11 citations
954. KG-FLIP: Knowledge-guided Fashion-domain Language-Image Pre-training for E-commerceIndustry11 citations
955. Know Where You’re Going: Meta-Learning for Parameter-Efficient Fine-TuningFindings11 citations
956. KoRC: Knowledge Oriented Reading Comprehension Benchmark for Deep Text UnderstandingFindings11 citations
957. Language Detoxification with Attribute-Discriminative Latent SpaceLong11 citations
958. Mars: Modeling Context & State Representations with Contrastive Learning for End-to-End Task-Oriented DialogFindings11 citations
959. MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African languagesLong11 citations
960. Medical Dialogue Generation via Dual Flow ModelingFindings11 citations
961. Moving Beyond Downstream Task Accuracy for Information Retrieval BenchmarkingFindings11 citations
962. NAG-NER: a Unified Non-Autoregressive Generation Framework for Various NER TasksIndustry11 citations
963. NewsMet : A ‘do it all’ Dataset of Contemporary Metaphors in News HeadlinesFindings11 citations
964. NollySenti: Leveraging Transfer Learning and Machine Translation for Nigerian Movie Sentiment ClassificationShort11 citations
965. On Isotropy, Contextualization and Learning Dynamics of Contrastive-based Sentence Representation LearningFindings11 citations
966. On the Efficacy of Sampling AdaptersLong11 citations
967. PLUE: Language Understanding Evaluation Benchmark for Privacy Policies in EnglishShort11 citations
968. Pay More Attention to Relation Exploration for Knowledge Base Question AnsweringFindings11 citations
969. RMLM: A Flexible Defense Framework for Proactively Mitigating Word-level Adversarial AttacksLong11 citations
970. Rethinking Round-Trip Translation for Machine Translation EvaluationFindings11 citations
971. SESCORE2: Learning Text Generation Evaluation via Synthesizing Realistic MistakesLong11 citations
972. Score It All Together: A Multi-Task Learning Study on Automatic Scoring of Argumentative EssaysFindings11 citations
973. Self-Evolution Learning for Discriminative Language Model PretrainingFindings11 citations
974. Sentiment Knowledge Enhanced Self-supervised Learning for Multimodal Sentiment AnalysisFindings11 citations
975. Similarity-weighted Construction of Contextualized Commonsense Knowledge Graphs for Knowledge-intense Argumentation TasksLong11 citations
976. StoryTrans: Non-Parallel Story Author-Style Transfer with Discourse Representations and Content EnhancingLong11 citations
977. TADA : Task Agnostic Dialect Adapters for EnglishFindings11 citations
978. TAGPRIME: A Unified Framework for Relational Structure ExtractionLong11 citations
979. TableVLM: Multi-modal Pre-training for Table Structure RecognitionLong11 citations
980. Tailoring Instructions to Student’s Learning Levels Boosts Knowledge DistillationLong11 citations
981. Target-Side Augmentation for Document-Level Machine TranslationLong11 citations
982. Towards Better Hierarchical Text Classification with Data GenerationFindings11 citations
983. Transformed Protoform ReconstructionShort11 citations
984. U-CREAT: Unsupervised Case Retrieval using Events extrAcTionLong11 citations
985. Unsupervised Keyphrase Extraction by Learning Neural Keyphrase Set FunctionFindings11 citations
986. A Crosslingual Investigation of Conceptualization in 1335 LanguagesLong10 citations
987. A Multi-modal Debiasing Model with Dynamical Constraint for Robust Visual Question AnsweringFindings10 citations
988. A Two-Stage Decoder for Efficient ICD CodingFindings10 citations
989. APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical ReasoningLong10 citations
990. Actively Supervised Clustering for Open Relation ExtractionLong10 citations
991. Adaptive Contrastive Knowledge Distillation for BERT CompressionFindings10 citations
992. Adversarial Multi-task Learning for End-to-end Metaphor DetectionFindings10 citations
993. Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language UnderstandingFindings10 citations
994. BADGE: Speeding Up BERT Inference after Deployment via Block-wise Bypasses and Divergence-based Early ExitingIndustry10 citations
995. Better Language Models of Code through Self-ImprovementFindings10 citations
996. Byte-Level Grammatical Error Correction Using Synthetic and Curated CorporaLong10 citations
997. CKDST: Comprehensively and Effectively Distill Knowledge from Machine Translation to End-to-End Speech TranslationFindings10 citations
998. Causal interventions expose implicit situation models for commonsense language understandingFindings10 citations
999. CoAD: Automatic Diagnosis through Symptom and Disease Collaborative GenerationLong10 citations
1000. Commonsense Knowledge Graph Completion Via Contrastive Pretraining and Node ClusteringFindings10 citations

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