EMNLP 2021 Accepted Papers

The full list of 1,311 papers accepted at EMNLP 2021 (Conference on Empirical Methods in Natural Language Processing). 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. The Power of Scale for Parameter-Efficient Prompt TuningMain4,341 citations
2. SimCSE: Simple Contrastive Learning of Sentence EmbeddingsMain3,717 citations
3. CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and GenerationMain1,707 citations
4. CLIPScore: A Reference-free Evaluation Metric for Image CaptioningMain1,494 citations
5. Retrieval Augmentation Reduces Hallucination in Conversationfinding762 citations
6. Transformer Feed-Forward Layers Are Key-Value MemoriesMain734 citations
7. VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text UnderstandingMain632 citations
8. Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled CorpusMain523 citations
9. Editing Factual Knowledge in Language ModelsMain486 citations
10. PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language ModelsMain397 citations
11. Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment AnalysisMain394 citations
12. REBEL: Relation Extraction By End-to-end Language generationfinding362 citations
13. Datasets: A Community Library for Natural Language ProcessingSystem Demonstrations325 citations
14. FinQA: A Dataset of Numerical Reasoning over Financial DataMain316 citations
15. Muppet: Massive Multi-task Representations with Pre-FinetuningMain305 citations
16. ONION: A Simple and Effective Defense Against Textual Backdoor AttacksMain293 citations
17. Want To Reduce Labeling Cost? GPT-3 Can Helpfinding291 citations
18. QuestEval: Summarization Asks for Fact-based EvaluationMain281 citations
19. RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingMain276 citations
20. Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for LittleMain275 citations
21. AdapterDrop: On the Efficiency of Adapters in TransformersMain268 citations
22. Condenser: a Pre-training Architecture for Dense RetrievalMain265 citations
23. GPT3Mix: Leveraging Large-scale Language Models for Text Augmentationfinding264 citations
24. Challenges in Detoxifying Language Modelsfinding256 citations
25. TSDAE: Using Transformer-based Sequential Denoising Auto-Encoderfor Unsupervised Sentence Embedding Learningfinding254 citations
26. Latent Hatred: A Benchmark for Understanding Implicit Hate SpeechMain249 citations
27. Fast WordPiece TokenizationMain247 citations
28. Aspect Sentiment Quad Prediction as Paraphrase GenerationMain243 citations
29. Gradient-based Adversarial Attacks against Text TransformersMain240 citations
30. Block Pruning For Faster TransformersMain238 citations
31. Generating Datasets with Pretrained Language ModelsMain237 citations
32. Entity-Based Knowledge Conflicts in Question AnsweringMain227 citations
33. Surface Form Competition: Why the Highest Probability Answer Isn’t Always RightMain227 citations
34. Active Learning by Acquiring Contrastive ExamplesMain217 citations
35. AEDA: An Easier Data Augmentation Technique for Text Classificationfinding210 citations
36. Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuningMain202 citations
37. Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Societyfinding194 citations
38. CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive SummarizationMain191 citations
39. Explaining Answers with Entailment TreesMain191 citations
40. Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style TransferMain191 citations
41. Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question AnsweringMain191 citations
42. Retrieval Augmented Code Generation and Summarizationfinding190 citations
43. TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph ForecastingMain190 citations
44. Measuring Association Between Labels and Free-Text RationalesMain188 citations
45. Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language TechnologiesMain185 citations
46. A Partition Filter Network for Joint Entity and Relation ExtractionMain176 citations
47. Visually Grounded Reasoning across Languages and CulturesMain175 citations
48. Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collectionsfinding173 citations
49. Contrastive Code Representation LearningMain167 citations
50. CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLPMain167 citations
51. Simple Entity-Centric Questions Challenge Dense RetrieversMain167 citations
52. XTREME-R: Towards More Challenging and Nuanced Multilingual EvaluationMain163 citations
53. Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their ConsequencesMain159 citations
54. Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path GroundingMain158 citations
55. Towards Improving Adversarial Training of NLP Modelsfinding158 citations
56. Improving and Simplifying Pattern Exploiting TrainingMain156 citations
57. Text2Mol: Cross-Modal Molecule Retrieval with Natural Language QueriesMain155 citations
58. Understanding and Overcoming the Challenges of Efficient Transformer QuantizationMain153 citations
59. Sustainable Modular Debiasing of Language Modelsfinding148 citations
60. Backdoor Attacks on Pre-trained Models by Layerwise Weight PoisoningMain143 citations
61. The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of TransformersMain142 citations
62. Few-Shot Text Generation with Natural Language InstructionsMain140 citations
63. Generate & Rank: A Multi-task Framework for Math Word Problemsfinding138 citations
64. Learning Neural Ordinary Equations for Forecasting Future Links on Temporal Knowledge GraphsMain138 citations
65. Label Verbalization and Entailment for Effective Zero and Few-Shot Relation ExtractionMain137 citations
66. Dialogue State Tracking with a Language Model using Schema-Driven PromptingMain136 citations
67. MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targetsfinding136 citations
68. The Perils of Using Mechanical Turk to Evaluate Open-Ended Text GenerationMain136 citations
69. Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-TrainingMain135 citations
70. Visual News: Benchmark and Challenges in News Image CaptioningMain134 citations
71. Continual Learning in Task-Oriented Dialogue SystemsMain133 citations
72. FastIF: Scalable Influence Functions for Efficient Model Interpretation and DebuggingMain133 citations
73. TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation GraphMain133 citations
74. MSˆ2: Multi-Document Summarization of Medical StudiesMain132 citations
75. N-LTP: An Open-source Neural Language Technology Platform for ChineseSystem Demonstrations131 citations
76. What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained TransformersMain130 citations
77. HittER: Hierarchical Transformers for Knowledge Graph EmbeddingsMain126 citations
78. Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence EncodersMain125 citations
79. Mitigating Language-Dependent Ethnic Bias in BERTMain125 citations
80. TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generationfinding125 citations
81. Joint Multi-modal Aspect-Sentiment Analysis with Auxiliary Cross-modal Relation DetectionMain124 citations
82. SituatedQA: Incorporating Extra-Linguistic Contexts into QAMain124 citations
83. Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine TranslationMain123 citations
84. Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inferencefinding122 citations
85. WhiteningBERT: An Easy Unsupervised Sentence Embedding Approachfinding122 citations
86. Evaluating the Robustness of Neural Language Models to Input PerturbationsMain119 citations
87. Narrative Theory for Computational Narrative UnderstandingMain119 citations
88. All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational QualityMain118 citations
89. Progressive Transformer-Based Generation of Radiology Reportsfinding118 citations
90. RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP ModelsMain118 citations
91. The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer EncodersMain118 citations
92. Contrastive Explanations for Model InterpretabilityMain117 citations
93. Do Transformer Modifications Transfer Across Implementations and Applications?Main117 citations
94. How to Train BERT with an Academic BudgetMain117 citations
95. A Plug-and-Play Method for Controlled Text Generationfinding116 citations
96. Improving Empathetic Response Generation by Recognizing Emotion Cause in Conversationsfinding116 citations
97. MultiEURLEX - A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transferMain116 citations
98. Few-Shot Named Entity Recognition: An Empirical Baseline StudyMain114 citations
99. ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual CorporaMain112 citations
100. What to Pre-Train on? Efficient Intermediate Task SelectionMain112 citations
101. Efficient Nearest Neighbor Language ModelsMain111 citations
102. ContractNLI: A Dataset for Document-level Natural Language Inference for Contractsfinding110 citations
103. Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators’ DisagreementMain108 citations
104. Competency Problems: On Finding and Removing Artifacts in Language DataMain108 citations
105. UNKs Everywhere: Adapting Multilingual Language Models to New ScriptsMain108 citations
106. Past, Present, and Future: Conversational Emotion Recognition through Structural Modeling of Psychological Knowledgefinding107 citations
107. Word-Level Coreference ResolutionMain107 citations
108. SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal ConversationsMain106 citations
109. WikiNEuRal: Combined Neural and Knowledge-based Silver Data Creation for Multilingual NERfinding106 citations
110. Building and Evaluating Open-Domain Dialogue Corpora with Clarifying QuestionsMain105 citations
111. Can Language Models be Biomedical Knowledge Bases?Main105 citations
112. Contrastive Out-of-Distribution Detection for Pretrained TransformersMain105 citations
113. Natural SQL: Making SQL Easier to Infer from Natural Language Specificationsfinding104 citations
114. Improving Question Answering Model Robustness with Synthetic Adversarial Data GenerationMain103 citations
115. Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image SearchMain102 citations
116. NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal MediaMain100 citations
117. Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text ClassificationMain100 citations
118. Types of Out-of-Distribution Texts and How to Detect ThemMain100 citations
119. Aspect-Controllable Opinion SummarizationMain99 citations
120. IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language GenerationMain98 citations
121. Paraphrase Generation: A Survey of the State of the ArtMain98 citations
122. A Novel Global Feature-Oriented Relational Triple Extraction Model based on Table FillingMain97 citations
123. Evidence-based Fact-Checking of Health-related Claimsfinding96 citations
124. SciCap: Generating Captions for Scientific Figuresfinding96 citations
125. Balancing Methods for Multi-label Text Classification with Long-Tailed Class DistributionMain95 citations
126. Data and Parameter Scaling Laws for Neural Machine TranslationMain95 citations
127. Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive ContextsMain95 citations
128. Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal TransformersMain94 citations
129. BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine TranslationMain93 citations
130. BERT4GCN: Using BERT Intermediate Layers to Augment GCN for Aspect-based Sentiment ClassificationMain93 citations
131. Less is More: Pretrain a Strong Siamese Encoder for Dense Text Retrieval Using a Weak DecoderMain93 citations
132. MATE: Multi-view Attention for Table Transformer EfficiencyMain93 citations
133. MultiDoc2Dial: Modeling Dialogues Grounded in Multiple DocumentsMain93 citations
134. Learning Compact Metrics for MTMain92 citations
135. Exploring Task Difficulty for Few-Shot Relation ExtractionMain91 citations
136. Few-Shot Intent Detection via Contrastive Pre-Training and Fine-TuningMain91 citations
137. On Pursuit of Designing Multi-modal Transformer for Video GroundingMain91 citations
138. Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus ExplorationMain91 citations
139. Revisiting the Uniform Information Density HypothesisMain90 citations
140. TAG: Gradient Attack on Transformer-based Language Modelsfinding90 citations
141. BARThez: a Skilled Pretrained French Sequence-to-Sequence ModelMain89 citations
142. Exploring Underexplored Limitations of Cross-Domain Text-to-SQL GeneralizationMain89 citations
143. IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary InitializationMain88 citations
144. Semi-supervised Relation Extraction via Incremental Meta Self-Trainingfinding88 citations
145. MAD-G: Multilingual Adapter Generation for Efficient Cross-Lingual Transferfinding87 citations
146. Weakly Supervised Contrastive Learning for Chest X-Ray Report Generationfinding87 citations
147. mT6: Multilingual Pretrained Text-to-Text Transformer with Translation PairsMain87 citations
148. ConSeC: Word Sense Disambiguation as Continuous Sense ComprehensionMain86 citations
149. Cross-Domain Label-Adaptive Stance DetectionMain86 citations
150. Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic FeaturesMain86 citations
151. Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive SummarizationMain85 citations
152. WebSRC: A Dataset for Web-Based Structural Reading ComprehensionMain85 citations
153. ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AIMain84 citations
154. Neural Media Bias Detection Using Distant Supervision With BABE - Bias Annotations By Expertsfinding84 citations
155. Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion CausesMain84 citations
156. Plan-then-Generate: Controlled Data-to-Text Generation via Planningfinding84 citations
157. A Simple and Effective Positional Encoding for TransformersMain83 citations
158. Rumor Detection on Twitter with Claim-Guided Hierarchical Graph Attention NetworksMain83 citations
159. Probing Across Time: What Does RoBERTa Know and When?finding82 citations
160. Case-based Reasoning for Natural Language Queries over Knowledge BasesMain81 citations
161. Constrained Language Models Yield Few-Shot Semantic ParsersMain80 citations
162. Incorporating medical knowledge in BERT for clinical relation extractionMain80 citations
163. Solving Aspect Category Sentiment Analysis as a Text Generation TaskMain80 citations
164. ECONET: Effective Continual Pretraining of Language Models for Event Temporal ReasoningMain79 citations
165. From Alignment to Assignment: Frustratingly Simple Unsupervised Entity AlignmentMain79 citations
166. Consistent Accelerated Inference via Confident Adaptive TransformersMain78 citations
167. Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-TrainingMain78 citations
168. Do Long-Range Language Models Actually Use Long-Range Context?Main78 citations
169. Efficient-FedRec: Efficient Federated Learning Framework for Privacy-Preserving News RecommendationMain78 citations
170. Learning and Evaluating a Differentially Private Pre-trained Language Modelfinding78 citations
171. SELFEXPLAIN: A Self-Explaining Architecture for Neural Text ClassifiersMain78 citations
172. Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language GenerationMain77 citations
173. Deep Attention Diffusion Graph Neural Networks for Text ClassificationMain77 citations
174. Frequency Effects on Syntactic Rule Learning in TransformersMain77 citations
175. Structural Adapters in Pretrained Language Models for AMR-to-Text GenerationMain77 citations
176. Diagnosing the First-Order Logical Reasoning Ability Through LogicNLIMain76 citations
177. Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question AnsweringMain76 citations
178. CDLM: Cross-Document Language Modelingfinding75 citations
179. LayoutReader: Pre-training of Text and Layout for Reading Order DetectionMain75 citations
180. Temporal Adaptation of BERT and Performance on Downstream Document Classification: Insights from Social Mediafinding75 citations
181. Topic-Aware Contrastive Learning for Abstractive Dialogue Summarizationfinding75 citations
182. MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative TasksMain74 citations
183. Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translationfinding73 citations
184. Machine Translation Decoding beyond Beam SearchMain73 citations
185. Searching for an Effective Defender: Benchmarking Defense against Adversarial Word SubstitutionMain72 citations
186. Unsupervised Keyphrase Extraction by Jointly Modeling Local and Global ContextMain72 citations
187. Inconsistency Matters: A Knowledge-guided Dual-inconsistency Network for Multi-modal Rumor Detectionfinding71 citations
188. Machine Reading Comprehension as Data Augmentation: A Case Study on Implicit Event Argument ExtractionMain71 citations
189. PASTE: A Tagging-Free Decoding Framework Using Pointer Networks for Aspect Sentiment Triplet ExtractionMain71 citations
190. Text Detoxification using Large Pre-trained Neural ModelsMain71 citations
191. CAST: Enhancing Code Summarization with Hierarchical Splitting and Reconstruction of Abstract Syntax TreesMain70 citations
192. Controllable Neural Dialogue Summarization with Personal Named Entity PlanningMain69 citations
193. Open Aspect Target Sentiment Classification with Natural Language PromptsMain69 citations
194. Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented SpeechMain69 citations
195. TDEER: An Efficient Translating Decoding Schema for Joint Extraction of Entities and RelationsMain69 citations
196. A Large-Scale Dataset for Empathetic Response GenerationMain68 citations
197. Document-level Entity-based Extraction as Template GenerationMain68 citations
198. Graph Based Network with Contextualized Representations of Turns in DialogueMain68 citations
199. Relational World Knowledge Representation in Contextual Language Models: A ReviewMain68 citations
200. Zero-Shot Dialogue State Tracking via Cross-Task TransferMain68 citations
201. CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification TasksMain67 citations
202. Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversationsfinding67 citations
203. The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event PredictionMain67 citations
204. Universal Sentence Representation Learning with Conditional Masked Language ModelMain67 citations
205. Weakly-supervised Text Classification Based on Keyword GraphMain67 citations
206. ‘Just What do You Think You’re Doing, Dave?’ A Checklist for Responsible Data Use in NLPfinding67 citations
207. Conditional probing: measuring usable information beyond a baselineMain66 citations
208. When Attention Meets Fast Recurrence: Training Language Models with Reduced ComputeMain66 citations
209. Discrete and Soft Prompting for Multilingual ModelsMain65 citations
210. DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational RecommendationMain65 citations
211. Effective Convolutional Attention Network for Multi-label Clinical Document ClassificationMain65 citations
212. Sequence Length is a Domain: Length-based Overfitting in Transformer ModelsMain65 citations
213. AttentionRank: Unsupervised Keyphrase Extraction using Self and Cross AttentionsMain64 citations
214. Gradient Imitation Reinforcement Learning for Low Resource Relation ExtractionMain64 citations
215. Improving End-to-End Task-Oriented Dialog System with A Simple Auxiliary Taskfinding64 citations
216. STraTA: Self-Training with Task Augmentation for Better Few-shot LearningMain64 citations
217. Learning Universal Authorship RepresentationsMain63 citations
218. Learning from Noisy Labels for Entity-Centric Information ExtractionMain63 citations
219. NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender Neutral AlternativesMain63 citations
220. OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word EmbeddingsMain63 citations
221. Time-aware Graph Neural Network for Entity Alignment between Temporal Knowledge GraphsMain63 citations
222. Automated Generation of Accurate & Fluent Medical X-ray ReportsMain62 citations
223. Contextualized Query Embeddings for Conversational SearchMain62 citations
224. Counter-Interference Adapter for Multilingual Machine Translationfinding62 citations
225. fBERT: A Neural Transformer for Identifying Offensive Contentfinding62 citations
226. Adaptive Proposal Generation Network for Temporal Sentence Localization in VideosMain61 citations
227. CR-Walker: Tree-Structured Graph Reasoning and Dialog Acts for Conversational RecommendationMain61 citations
228. Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answeringfinding61 citations
229. SentNoB: A Dataset for Analysing Sentiment on Noisy Bangla Textsfinding61 citations
230. An Exploratory Study on Long Dialogue Summarization: What Works and What’s Nextfinding60 citations
231. Can NLI Models Verify QA Systems’ Predictions?finding60 citations
232. Discretized Integrated Gradients for Explaining Language ModelsMain60 citations
233. ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense ReasoningMain60 citations
234. Relation-aware Video Reading Comprehension for Temporal Language GroundingMain60 citations
235. Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language ModelsMain59 citations
236. Pairwise Supervised Contrastive Learning of Sentence RepresentationsMain59 citations
237. TransPrompt: Towards an Automatic Transferable Prompting Framework for Few-shot Text ClassificationMain59 citations
238. Automatic Text Evaluation through the Lens of Wasserstein BarycentersMain58 citations
239. Cross-lingual Aspect-based Sentiment Analysis with Aspect Term Code-SwitchingMain58 citations
240. DWUG: A large Resource of Diachronic Word Usage Graphs in Four LanguagesMain58 citations
241. Finetuning Pretrained Transformers into RNNsMain58 citations
242. Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous EnvironmentsMain58 citations
243. Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd SchemaMain57 citations
244. Dimensional Emotion Detection from Categorical EmotionMain57 citations
245. Document-Level Text Simplification: Dataset, Criteria and BaselineMain57 citations
246. MassiveSumm: a very large-scale, very multilingual, news summarisation datasetMain57 citations
247. Perturbation CheckLists for Evaluating NLG Evaluation MetricsMain57 citations
248. The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translationfinding57 citations
249. Artificial Text Detection via Examining the Topology of Attention MapsMain56 citations
250. Dealing with Typos for BERT-based Passage Retrieval and RankingMain56 citations
251. Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State TrackingMain56 citations
252. Natural Language Video Localization with Learnable Moment ProposalsMain56 citations
253. Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question AnsweringMain56 citations
254. A Discourse-Aware Graph Neural Network for Emotion Recognition in Multi-Party Conversationfinding55 citations
255. English Machine Reading Comprehension Datasets: A SurveyMain55 citations
256. Evaluating Debiasing Techniques for Intersectional BiasesMain55 citations
257. Hierarchical Heterogeneous Graph Representation Learning for Short Text ClassificationMain55 citations
258. LM-Critic: Language Models for Unsupervised Grammatical Error CorrectionMain55 citations
259. AESOP: Paraphrase Generation with Adaptive Syntactic ControlMain54 citations
260. Data Augmentation for Cross-Domain Named Entity RecognitionMain54 citations
261. Integrating Visuospatial, Linguistic, and Commonsense Structure into Story VisualizationMain54 citations
262. Phrase Retrieval Learns Passage Retrieval, TooMain54 citations
263. BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of BeliefMain53 citations
264. Improving Unsupervised Question Answering via Summarization-Informed Question GenerationMain53 citations
265. Models and Datasets for Cross-Lingual SummarisationMain53 citations
266. Multimodal Phased Transformer for Sentiment AnalysisMain53 citations
267. Broaden the Vision: Geo-Diverse Visual Commonsense ReasoningMain52 citations
268. Effectiveness of Pre-training for Few-shot Intent Classificationfinding52 citations
269. Factual Consistency Evaluation for Text Summarization via Counterfactual Estimationfinding52 citations
270. FewshotQA: A simple framework for few-shot learning of question answering tasks using pre-trained text-to-text modelsMain52 citations
271. Math Word Problem Generation with Mathematical Consistency and Problem Context ConstraintsMain52 citations
272. Named Entity Recognition for Entity Linking: What Works and What’s Nextfinding52 citations
273. Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT CompressionMain51 citations
274. GooAQ: Open Question Answering with Diverse Answer Typesfinding51 citations
275. Learning Neural Templates for Recommender Dialogue SystemMain51 citations
276. Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformersfinding51 citations
277. UniKER: A Unified Framework for Combining Embedding and Definite Horn Rule Reasoning for Knowledge Graph InferenceMain51 citations
278. Answering Open-Domain Questions of Varying Reasoning Steps from TextMain50 citations
279. CRFR: Improving Conversational Recommender Systems via Flexible Fragments Reasoning on Knowledge GraphsMain50 citations
280. Parallel Refinements for Lexically Constrained Text Generation with BARTMain50 citations
281. SpellBERT: A Lightweight Pretrained Model for Chinese Spelling CheckMain50 citations
282. Improving Multimodal fusion via Mutual Dependency MaximisationMain49 citations
283. Incorporating Residual and Normalization Layers into Analysis of Masked Language ModelsMain49 citations
284. Progressive Self-Training with Discriminator for Aspect Term ExtractionMain49 citations
285. Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence GroundingMain49 citations
286. Sparse Attention with Linear UnitsMain49 citations
287. Uncovering Main Causalities for Long-tailed Information ExtractionMain49 citations
288. Zero-Shot Cross-Lingual Transfer of Neural Machine Translation with Multilingual Pretrained EncodersMain49 citations
289. CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascadefinding48 citations
290. Convex Aggregation for Opinion Summarizationfinding48 citations
291. Cross Attention Augmented Transducer Networks for Simultaneous TranslationMain48 citations
292. Effective Sequence-to-Sequence Dialogue State TrackingMain48 citations
293. Neuro-Symbolic Reinforcement Learning with First-Order LogicMain48 citations
294. Revisiting Self-training for Few-shot Learning of Language ModelMain48 citations
295. AStitchInLanguageModels: Dataset and Methods for the Exploration of Idiomaticity in Pre-Trained Language Modelsfinding47 citations
296. Controllable Semantic Parsing via Retrieval AugmentationMain47 citations
297. Dynamic Knowledge Distillation for Pre-trained Language ModelsMain47 citations
298. Finding a Balanced Degree of Automation for Summary EvaluationMain47 citations
299. Multi-Class Grammatical Error Detection for Correction: A Tale of Two SystemsMain47 citations
300. Multi-Modal Open-Domain DialogueMain47 citations
301. Multilingual Unsupervised Neural Machine Translation with Denoising AdaptersMain47 citations
302. NewsBERT: Distilling Pre-trained Language Model for Intelligent News Applicationfinding47 citations
303. RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition ModelsMain47 citations
304. Simple Conversational Data Augmentation for Semi-supervised Abstractive Dialogue SummarizationMain47 citations
305. Speaker Turn Modeling for Dialogue Act Classificationfinding47 citations
306. Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherencefinding47 citations
307. Unsupervised Paraphrasing with Pretrained Language ModelsMain47 citations
308. When differential privacy meets NLP: The devil is in the detailMain47 citations
309. “Let Your Characters Tell Their Story”: A Dataset for Character-Centric Narrative Understandingfinding47 citations
310. Does Putting a Linguist in the Loop Improve NLU Data Collection?finding46 citations
311. Improving Math Word Problems with Pre-trained Knowledge and Hierarchical ReasoningMain46 citations
312. Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge GraphsMain46 citations
313. Utilizing Relative Event Time to Enhance Event-Event Temporal Relation ExtractionMain46 citations
314. What Does Your Smile Mean? Jointly Detecting Multi-Modal Sarcasm and Sentiment Using Quantum Probabilityfinding46 citations
315. BiQUE: Biquaternionic Embeddings of Knowledge GraphsMain45 citations
316. CSDS: A Fine-Grained Chinese Dataset for Customer Service Dialogue SummarizationMain45 citations
317. Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLPMain45 citations
318. Does Pretraining for Summarization Require Knowledge Transfer?finding45 citations
319. Fight Fire with Fire: Fine-tuning Hate Detectors using Large Samples of Generated Hate Speechfinding45 citations
320. Improving Zero-Shot Cross-Lingual Transfer Learning via Robust TrainingMain45 citations
321. Mixture-of-Partitions: Infusing Large Biomedical Knowledge Graphs into BERTMain45 citations
322. Multiplex Graph Neural Network for Extractive Text SummarizationMain45 citations
323. R2-D2: A Modular Baseline for Open-Domain Question Answeringfinding45 citations
324. RuleBERT: Teaching Soft Rules to Pre-Trained Language ModelsMain45 citations
325. SHAPE: Shifted Absolute Position Embedding for TransformersMain45 citations
326. STANKER: Stacking Network based on Level-grained Attention-masked BERT for Rumor Detection on Social MediaMain45 citations
327. Shortcutted Commonsense: Data Spuriousness in Deep Learning of Commonsense ReasoningMain45 citations
328. Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR ParsingMain45 citations
329. Text AutoAugment: Learning Compositional Augmentation Policy for Text ClassificationMain45 citations
330. Zero-Shot Information Extraction as a Unified Text-to-Triple TranslationMain45 citations
331. Cartography Active Learningfinding44 citations
332. Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learningfinding44 citations
333. MapRE: An Effective Semantic Mapping Approach for Low-resource Relation ExtractionMain44 citations
334. TWEETSUMM - A Dialog Summarization Dataset for Customer Servicefinding44 citations
335. Visual Goal-Step Inference using wikiHowMain44 citations
336. A Relation-Oriented Clustering Method for Open Relation ExtractionMain43 citations
337. Adaptive Information Seeking for Open-Domain Question AnsweringMain43 citations
338. An Iterative Multi-Knowledge Transfer Network for Aspect-Based Sentiment Analysisfinding43 citations
339. Highly Parallel Autoregressive Entity Linking with Discriminative CorrectionMain43 citations
340. Improving Multilingual Translation by Representation and Gradient RegularizationMain43 citations
341. Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge ResourcesMain43 citations
342. Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Frameworkfinding43 citations
343. Robust Open-Vocabulary Translation from Visual Text RepresentationsMain43 citations
344. Timeline Summarization based on Event Graph Compression via Time-Aware Optimal TransportMain43 citations
345. Uncertainty-Aware Machine Translation Evaluationfinding43 citations
346. Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lensfinding43 citations
347. Definition Modelling for Appropriate SpecificityMain42 citations
348. Enriching and Controlling Global Semantics for Text SummarizationMain42 citations
349. How much pretraining data do language models need to learn syntax?Main42 citations
350. Implicit Sentiment Analysis with Event-centered Text RepresentationMain42 citations
351. Jump-Starting Item Parameters for Adaptive Language TestsMain42 citations
352. LightTag: Text Annotation PlatformSystem Demonstrations42 citations
353. Low-Resource Dialogue Summarization with Domain-Agnostic Multi-Source PretrainingMain42 citations
354. To be Closer: Learning to Link up Aspects with OpinionsMain42 citations
355. Enhanced Language Representation with Label Knowledge for Span ExtractionMain41 citations
356. Identifying Morality Frames in Political Tweets using Relational LearningMain41 citations
357. Learning Logic Rules for Document-Level Relation ExtractionMain41 citations
358. Model-based analysis of brain activity reveals the hierarchy of language in 305 subjectsfinding41 citations
359. A Strong Baseline for Query Efficient Attacks in a Black Box SettingMain40 citations
360. Contrastive Domain Adaptation for Question Answering using Limited Text CorporaMain40 citations
361. Joint Passage Ranking for Diverse Multi-Answer RetrievalMain40 citations
362. Knowledge-Interactive Network with Sentiment Polarity Intensity-Aware Multi-Task Learning for Emotion Recognition in Conversationsfinding40 citations
363. Large-Scale Relation Learning for Question Answering over Knowledge Bases with Pre-trained Language ModelsMain40 citations
364. Monolingual and Cross-Lingual Acceptability Judgments with the Italian CoLA corpusfinding40 citations
365. Rationales for Sequential PredictionsMain40 citations
366. AligNART: Non-autoregressive Neural Machine Translation by Jointly Learning to Estimate Alignment and TranslateMain39 citations
367. An Edge-Enhanced Hierarchical Graph-to-Tree Network for Math Word Problem Solvingfinding39 citations
368. Asking It All: Generating Contextualized Questions for any Semantic RoleMain39 citations
369. Attribute Alignment: Controlling Text Generation from Pre-trained Language Modelsfinding39 citations
370. ChemNER: Fine-Grained Chemistry Named Entity Recognition with Ontology-Guided Distant SupervisionMain39 citations
371. Distilling Linguistic Context for Language Model CompressionMain39 citations
372. Exploring Sentence Community for Document-Level Event Extractionfinding39 citations
373. Hyperbolic Hierarchy-Aware Knowledge Graph Embedding for Link Predictionfinding39 citations
374. Mathematical Word Problem Generation from Commonsense Knowledge Graph and EquationsMain39 citations
375. Robust Retrieval Augmented Generation for Zero-shot Slot FillingMain39 citations
376. Semantics-Preserved Data Augmentation for Aspect-Based Sentiment AnalysisMain39 citations
377. StreamHover: Livestream Transcript Summarization and AnnotationMain39 citations
378. A surprisal–duration trade-off across and within the world’s languagesMain38 citations
379. Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLPMain38 citations
380. Compositional Generalization via Semantic Taggingfinding38 citations
381. DialogueCSE: Dialogue-based Contrastive Learning of Sentence EmbeddingsMain38 citations
382. Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information ExtractionMain38 citations
383. Generating Realistic Natural Language Counterfactualsfinding38 citations
384. Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updatesfinding38 citations
385. Learning with Different Amounts of Annotation: From Zero to Many LabelsMain38 citations
386. Multi-granularity Textual Adversarial Attack with Behavior CloningMain38 citations
387. Topic-Guided Abstractive Multi-Document Summarizationfinding38 citations
388. RollingLDA: An Update Algorithm of Latent Dirichlet Allocation to Construct Consistent Time Series from Textual Datafinding37 citations
389. AVocaDo: Strategy for Adapting Vocabulary to Downstream DomainMain36 citations
390. Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal InterventionMain36 citations
391. On the Complementarity between Pre-Training and Back-Translation for Neural Machine Translationfinding36 citations
392. P-INT: A Path-based Interaction Model for Few-shot Knowledge Graph Completionfinding36 citations
393. Recall and Learn: A Memory-augmented Solver for Math Word Problemsfinding36 citations
394. Sorting through the noise: Testing robustness of information processing in pre-trained language modelsMain36 citations
395. The World of an Octopus: How Reporting Bias Influences a Language Model’s Perception of ColorMain36 citations
396. ConvFiT: Conversational Fine-Tuning of Pretrained Language ModelsMain35 citations
397. DILBERT: Customized Pre-Training for Domain Adaptation with Category Shift, with an Application to Aspect ExtractionMain35 citations
398. Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL ParsingMain35 citations
399. Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretablefinding35 citations
400. Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through LexicaMain35 citations
401. Euphemistic Phrase Detection by Masked Language Modelfinding35 citations
402. Fairness-aware Class Imbalanced LearningMain35 citations
403. HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive SummarizationMain35 citations
404. Improving Neural Machine Translation by Bidirectional TrainingMain35 citations
405. IndoNLI: A Natural Language Inference Dataset for IndonesianMain35 citations
406. KERS: A Knowledge-Enhanced Framework for Recommendation Dialog Systems with Multiple Subgoalsfinding35 citations
407. Low-resource Taxonomy Enrichment with Pretrained Language ModelsMain35 citations
408. ReasonBERT: Pre-trained to Reason with Distant SupervisionMain35 citations
409. Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning ApproachMain35 citations
410. Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understandingfinding35 citations
411. A Thorough Evaluation of Task-Specific Pretraining for SummarizationMain34 citations
412. Corpus-based Open-Domain Event Type InductionMain34 citations
413. Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient DescentMain34 citations
414. Efficient Test Time Adapter Ensembling for Low-resource Language Varietiesfinding34 citations
415. Entity Relation Extraction as Dependency Parsing in Visually Rich DocumentsMain34 citations
416. Extracting Event Temporal Relations via Hyperbolic GeometryMain34 citations
417. Fine-grained Entity Typing via Label ReasoningMain34 citations
418. Importance Estimation from Multiple Perspectives for Keyphrase ExtractionMain34 citations
419. Improved Word Sense Disambiguation with Enhanced Sense Representationsfinding34 citations
420. Language Models are Few-Shot ButlersMain34 citations
421. Learning Opinion Summarizers by Selecting Informative ReviewsMain34 citations
422. Learning Prototype Representations Across Few-Shot Tasks for Event DetectionMain34 citations
423. Lifelong Event Detection with Knowledge TransferMain34 citations
424. Parameter-Efficient Domain Knowledge Integration from Multiple Sources for Biomedical Pre-trained Language Modelsfinding34 citations
425. Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k PolicyMain34 citations
426. fairseq Sˆ2: A Scalable and Integrable Speech Synthesis ToolkitSystem Demonstrations34 citations
427. Abstract, Rationale, Stance: A Joint Model for Scientific Claim VerificationMain33 citations
428. Assessing the Reliability of Word Embedding Gender Bias MeasuresMain33 citations
429. BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networksfinding33 citations
430. Combining Curriculum Learning and Knowledge Distillation for Dialogue Generationfinding33 citations
431. DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document ContextualizationMain33 citations
432. Distilling Knowledge for Empathy Detectionfinding33 citations
433. Does Vision-and-Language Pretraining Improve Lexical Grounding?finding33 citations
434. Few-Shot Table-to-Text Generation with Prototype Memoryfinding33 citations
435. Moving on from OntoNotes: Coreference Resolution Model TransferMain33 citations
436. Multi-stage Training with Improved Negative Contrast for Neural Passage RetrievalMain33 citations
437. Multilingual and Cross-Lingual Intent Detection from Spoken DataMain33 citations
438. Predicting Anti-Asian Hateful Users on Twitter during COVID-19finding33 citations
439. Sentence Bottleneck Autoencoders from Transformer Language ModelsMain33 citations
440. TIAGE: A Benchmark for Topic-Shift Aware Dialog Modelingfinding33 citations
441. Wav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognitionfinding33 citations
442. A Bag of Tricks for Dialogue SummarizationMain32 citations
443. An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words ExtractionMain32 citations
444. Asking Questions Like Educational Experts: Automatically Generating Question-Answer Pairs on Real-World Examination DataMain32 citations
445. CAPE: Context-Aware Private Embeddings for Private Language LearningMain32 citations
446. Crosslingual Transfer Learning for Relation and Event Extraction via Word Category and Class AlignmentsMain32 citations
447. Evaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality TransferMain32 citations
448. Exposure Bias versus Self-Recovery: Are Distortions Really Incremental for Autoregressive Text Generation?Main32 citations
449. Flexible Generation of Natural Language DeductionsMain32 citations
450. Frustratingly Simple Pretraining Alternatives to Masked Language ModelingMain32 citations
451. Iterative GNN-based Decoder for Question GenerationMain32 citations
452. Joint Multimedia Event Extraction from Video and Articlefinding32 citations
453. Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMTMain32 citations
454. Learning to Rewrite for Non-Autoregressive Neural Machine TranslationMain32 citations
455. MLEC-QA: A Chinese Multi-Choice Biomedical Question Answering DatasetMain32 citations
456. Measuring Sentence-Level and Aspect-Level (Un)certainty in Science CommunicationsMain32 citations
457. Modeling Document-Level Context for Event Detection via Important Context SelectionMain32 citations
458. RICA: Evaluating Robust Inference Capabilities Based on Commonsense AxiomsMain32 citations
459. Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstrationfinding32 citations
460. Refocusing on Relevance: Personalization in NLGMain32 citations
461. Rethinking Why Intermediate-Task Fine-Tuning Worksfinding32 citations
462. Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue SystemsMain32 citations
463. Aligning Cross-lingual Sentence Representations with Dual Momentum ContrastMain31 citations
464. Avoiding Inference Heuristics in Few-shot Prompt-based FinetuningMain31 citations
465. Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot FillingMain31 citations
466. Hierarchical Multi-label Text Classification with Horizontal and Vertical Category CorrelationsMain31 citations
467. Improving Stance Detection with Multi-Dataset Learning and Knowledge DistillationMain31 citations
468. Inducing Transformer’s Compositional Generalization Ability via Auxiliary Sequence Prediction TasksMain31 citations
469. KLMo: Knowledge Graph Enhanced Pretrained Language Model with Fine-Grained Relationshipsfinding31 citations
470. Learning Kernel-Smoothed Machine Translation with Retrieved ExamplesMain31 citations
471. Neural News Recommendation with Collaborative News Encoding and Structural User Encodingfinding31 citations
472. Perceived and Intended Sarcasm Detection with Graph Attention Networksfinding31 citations
473. SPECTRA: Sparse Structured Text RationalizationMain31 citations
474. Seeking Common but Distinguishing Difference, A Joint Aspect-based Sentiment Analysis ModelMain31 citations
475. Think about it! Improving defeasible reasoning by first modeling the question scenario.Main31 citations
476. A Model of Cross-Lingual Knowledge-Grounded Response Generation for Open-Domain Dialogue Systemsfinding30 citations
477. A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue GenerationMain30 citations
478. Adversarial Examples for Evaluating Math Word Problem Solversfinding30 citations
479. AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African LanguagesMain30 citations
480. An Unsupervised Method for Building Sentence Simplification Corpora in Multiple Languagesfinding30 citations
481. BFClass: A Backdoor-free Text Classification Frameworkfinding30 citations
482. BPM_MT: Enhanced Backchannel Prediction Model using Multi-Task LearningMain30 citations
483. Context-aware Entity Typing in Knowledge Graphsfinding30 citations
484. Controlling Machine Translation for Multiple Attributes with Additive InterventionsMain30 citations
485. Cost-effective End-to-end Information Extraction for Semi-structured Document ImagesMain30 citations
486. CrossVQA: Scalably Generating Benchmarks for Systematically Testing VQA GeneralizationMain30 citations
487. Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic EvaluationMain30 citations
488. Dense Hierarchical Retrieval for Open-domain Question Answeringfinding30 citations
489. Document Graph for Neural Machine TranslationMain30 citations
490. Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language ModelsMain30 citations
491. Few-Shot Emotion Recognition in Conversation with Sequential Prototypical NetworksMain30 citations
492. GOLD: Improving Out-of-Scope Detection in Dialogues using Data AugmentationMain30 citations
493. How Does Counterfactually Augmented Data Impact Models for Social Computing Constructs?Main30 citations
494. Is Everything in Order? A Simple Way to Order SentencesMain30 citations
495. Journalistic Guidelines Aware News Image CaptioningMain30 citations
496. Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue GenerationMain30 citations
497. Optimal Neural Program Synthesis from Multimodal Specificationsfinding30 citations
498. Uncovering the Limits of Text-based Emotion Detectionfinding30 citations
499. Which is Making the Contribution: Modulating Unimodal and Cross-modal Dynamics for Multimodal Sentiment Analysisfinding30 citations
500. A Bayesian Framework for Information-Theoretic ProbingMain29 citations
501. A Generative Framework for Simultaneous Machine TranslationMain29 citations
502. A Large-Scale Study of Machine Translation in Turkic LanguagesMain29 citations
503. Achieving Model Robustness through Discrete Adversarial TrainingMain29 citations
504. Constructing Emotional Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generationfinding29 citations
505. Cross-Domain Data Integration for Named Entity Disambiguation in Biomedical Textfinding29 citations
506. Cross-Modal Retrieval Augmentation for Multi-Modal Classificationfinding29 citations
507. Exploiting Reasoning Chains for Multi-hop Science Question Answeringfinding29 citations
508. FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale GenerationMain29 citations
509. Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic FactorsMain29 citations
510. HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learningfinding29 citations
511. Integrating Deep Event-Level and Script-Level Information for Script Event PredictionMain29 citations
512. MTAdam: Automatic Balancing of Multiple Training Loss TermsMain29 citations
513. MURAL: Multimodal, Multitask Representations Across Languagesfinding29 citations
514. MeLT: Message-Level Transformer with Masked Document Representations as Pre-Training for Stance Detectionfinding29 citations
515. Mutual-Learning Improves End-to-End Speech TranslationMain29 citations
516. Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translationfinding29 citations
517. Pre-train or Annotate? Domain Adaptation with a Constrained BudgetMain29 citations
518. Self-Attention Graph Residual Convolutional Networks for Event Detection with dependency relationsfinding29 citations
519. Simple and Effective Unsupervised Redundancy Elimination to Compress Dense Vectors for Passage RetrievalMain29 citations
520. Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge DistillationMain29 citations
521. Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference ResolutionMain29 citations
522. “Be nice to your wife! The restaurants are closed”: Can Gender Stereotype Detection Improve Sexism Classification?finding29 citations
523. Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution MethodsMain28 citations
524. COVR: A Test-Bed for Visually Grounded Compositional Generalization with Real ImagesMain28 citations
525. CodRED: A Cross-Document Relation Extraction Dataset for Acquiring Knowledge in the WildMain28 citations
526. Exploring the Role of BERT Token Representations to Explain Sentence Probing ResultsMain28 citations
527. Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional GeneralizationMain28 citations
528. Human Rationales as Attribution Priors for Explainable Stance DetectionMain28 citations
529. HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledgefinding28 citations
530. Improving Federated Learning for Aspect-based Sentiment Analysis via Topic MemoriesMain28 citations
531. KFCNet: Knowledge Filtering and Contrastive Learning for Generative Commonsense Reasoningfinding28 citations
532. More is Better: Enhancing Open-Domain Dialogue Generation via Multi-Source Heterogeneous KnowledgeMain28 citations
533. Multitask Semi-Supervised Learning for Class-Imbalanced Discourse ClassificationMain28 citations
534. On the Transferability of Adversarial Attacks against Neural Text ClassifierMain28 citations
535. Self- and Pseudo-self-supervised Prediction of Speaker and Key-utterance for Multi-party Dialogue Reading Comprehensionfinding28 citations
536. SeqAttack: On Adversarial Attacks for Named Entity RecognitionSystem Demonstrations28 citations
537. Towards Zero-Shot Knowledge Distillation for Natural Language ProcessingMain28 citations
538. Code-switched inspired losses for spoken dialog representationsMain27 citations
539. Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decodingfinding27 citations
540. Distilling Relation Embeddings from Pretrained Language ModelsMain27 citations
541. Distributionally Robust Multilingual Machine TranslationMain27 citations
542. EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillationfinding27 citations
543. Genre as Weak Supervision for Cross-lingual Dependency ParsingMain27 citations
544. Have You Seen That Number? Investigating Extrapolation in Question Answering ModelsMain27 citations
545. I Wish I Would Have Loved This One, But I Didn’t – A Multilingual Dataset for Counterfactual Detection in Product ReviewMain27 citations
546. Idiosyncratic but not Arbitrary: Learning Idiolects in Online Registers Reveals Distinctive yet Consistent Individual StylesMain27 citations
547. Injecting Entity Types into Entity-Guided Text GenerationMain27 citations
548. Neural Machine Translation Quality and Post-Editing PerformanceMain27 citations
549. SD-QA: Spoken Dialectal Question Answering for the Real Worldfinding27 citations
550. Single-dataset Experts for Multi-dataset Question AnsweringMain27 citations
551. Stepmothers are mean and academics are pretentious: What do pretrained language models learn about you?Main27 citations
552. TEMP: Taxonomy Expansion with Dynamic Margin Loss through Taxonomy-PathsMain27 citations
553. Unsupervised Conversation Disentanglement through Co-TrainingMain27 citations
554. Unsupervised Data Augmentation with Naive Augmentation and without Unlabeled DataMain27 citations
555. ValNorm Quantifies Semantics to Reveal Consistent Valence Biases Across Languages and Over CenturiesMain27 citations
556. What happens if you treat ordinal ratings as interval data? Human evaluations in NLP are even more under-powered than you thinkMain27 citations
557. What’s in a Name? Answer Equivalence For Open-Domain Question AnsweringMain27 citations
558. A Semantic Feature-Wise Transformation Relation Network for Automatic Short Answer GradingMain26 citations
559. ActiveEA: Active Learning for Neural Entity AlignmentMain26 citations
560. Aligning Actions Across Recipe GraphsMain26 citations
561. Allocating Large Vocabulary Capacity for Cross-Lingual Language Model Pre-TrainingMain26 citations
562. Beta Distribution Guided Aspect-aware Graph for Aspect Category Sentiment Analysis with Affective KnowledgeMain26 citations
563. CoLV: A Collaborative Latent Variable Model for Knowledge-Grounded Dialogue GenerationMain26 citations
564. CodeQA: A Question Answering Dataset for Source Code Comprehensionfinding26 citations
565. ConRPG: Paraphrase Generation using Contexts as RegularizerMain26 citations
566. Cross-lingual Sentence Embedding using Multi-Task LearningMain26 citations
567. Efficient Contrastive Learning via Novel Data Augmentation and Curriculum LearningMain26 citations
568. Exploring Decomposition for Table-based Fact Verificationfinding26 citations
569. Filling the Gaps in Ancient Akkadian Texts: A Masked Language Modelling ApproachMain26 citations
570. ForumSum: A Multi-Speaker Conversation Summarization Datasetfinding26 citations
571. Heterogeneous Graph Neural Networks for Keyphrase GenerationMain26 citations
572. Learning Constraints and Descriptive Segmentation for Subevent DetectionMain26 citations
573. Multilingual Translation via Grafting Pre-trained Language Modelsfinding26 citations
574. PDALN: Progressive Domain Adaptation over a Pre-trained Model for Low-Resource Cross-Domain Named Entity RecognitionMain26 citations
575. Project Debater APIs: Decomposing the AI Grand ChallengeSystem Demonstrations26 citations
576. RoR: Read-over-Read for Long Document Machine Reading Comprehensionfinding26 citations
577. Say ‘YES’ to Positivity: Detecting Toxic Language in Workplace Communicationsfinding26 citations
578. Speechformer: Reducing Information Loss in Direct Speech TranslationMain26 citations
579. T3-Vis: visual analytic for Training and fine-Tuning Transformers in NLPSystem Demonstrations26 citations
580. Transductive Learning for Unsupervised Text Style TransferMain26 citations
581. We Need to Talk About train-dev-test SplitsMain26 citations
582. BiSECT: Learning to Split and Rephrase Sentences with BitextsMain25 citations
583. Coarse2Fine: Fine-grained Text Classification on Coarsely-grained Annotated DataMain25 citations
584. Compositional Networks Enable Systematic Generalization for Grounded Language Understandingfinding25 citations
585. Data Efficient Masked Language Modeling for Vision and Languagefinding25 citations
586. Disentangling Generative Factors in Natural Language with Discrete Variational Autoencodersfinding25 citations
587. HAConvGNN: Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in Jupyter Notebooksfinding25 citations
588. How much coffee was consumed during EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AIMain25 citations
589. Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning InterpretabilityMain25 citations
590. Numeracy enhances the Literacy of Language ModelsMain25 citations
591. Relation Extraction with Word Graphs from N-gramsMain25 citations
592. Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsingfinding25 citations
593. Systematic Generalization on gSCAN: What is Nearly Solved and What is Next?Main25 citations
594. Time-dependent Entity Embedding is not All You Need: A Re-evaluation of Temporal Knowledge Graph Completion Models under a Unified FrameworkMain25 citations
595. To Protect and To Serve? Analyzing Entity-Centric Framing of Police Violencefinding25 citations
596. Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Datafinding25 citations
597. VeeAlign: Multifaceted Context Representation Using Dual Attention for Ontology AlignmentMain25 citations
598. Vision Matters When It Should: Sanity Checking Multimodal Machine Translation ModelsMain25 citations
599. Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question AnsweringMain25 citations
600. A Computational Exploration of Pejorative Language in Social Mediafinding24 citations
601. A Secure and Efficient Federated Learning Framework for NLPMain24 citations
602. CRYPTOGRU: Low Latency Privacy-Preserving Text Analysis With GRUMain24 citations
603. DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational TransformerMain24 citations
604. Discovering the Unknown Knowns: Turning Implicit Knowledge in the Dataset into Explicit Training Examples for Visual Question AnsweringMain24 citations
605. Disentangling Representations of Text by Masking TransformersMain24 citations
606. End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge GraphsMain24 citations
607. Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddingsfinding24 citations
608. Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising LearningMain24 citations
609. Investigating Robustness of Dialog Models to Popular Figurative Language ConstructsMain24 citations
610. Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation ExtractionMain24 citations
611. ODIST: Open World Classification via Distributionally Shifted Instancesfinding24 citations
612. SgSum:Transforming Multi-document Summarization into Sub-graph SelectionMain24 citations
613. Simulated Chats for Building Dialog Systems: Learning to Generate Conversations from Instructionsfinding24 citations
614. The Topic Confusion Task: A Novel Evaluation Scenario for Authorship Attributionfinding24 citations
615. Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation ApproachMain24 citations
616. Uni-FedRec: A Unified Privacy-Preserving News Recommendation Framework for Model Training and Online Servingfinding24 citations
617. Using Question Answering Rewards to Improve Abstractive Summarizationfinding24 citations
618. An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Fillingfinding23 citations
619. Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation DatasetMain23 citations
620. Bidirectional Hierarchical Attention Networks based on Document-level Context for Emotion Cause Extractionfinding23 citations
621. Caption Enriched Samples for Improving Hateful Memes DetectionMain23 citations
622. Comparative Opinion Quintuple Extraction from Product ReviewsMain23 citations
623. Connecting Attributions and QA Model Behavior on Realistic CounterfactualsMain23 citations
624. Considering Nested Tree Structure in Sentence Extractive Summarization with Pre-trained TransformerMain23 citations
625. Contrastive Conditioning for Assessing Disambiguation in MT: A Case Study of Distilled BiasMain23 citations
626. Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extractionfinding23 citations
627. Encouraging Lexical Translation Consistency for Document-Level Neural Machine TranslationMain23 citations
628. Exploring Methods for Generating Feedback Comments for Writing LearningMain23 citations
629. FLiText: A Faster and Lighter Semi-Supervised Text Classification with Convolution NetworksMain23 citations
630. Integrating Semantic Scenario and Word Relations for Abstractive Sentence SummarizationMain23 citations
631. Layer-wise Model Pruning based on Mutual InformationMain23 citations
632. Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Modelfinding23 citations
633. Patterns of Polysemy and Homonymy in Contextualised Language Modelsfinding23 citations
634. ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language ModelsMain23 citations
635. Reference-Centric Models for Grounded Collaborative DialogueMain23 citations
636. Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variablesfinding23 citations
637. A Simple and Effective Method To Eliminate the Self Language Bias in Multilingual RepresentationsMain22 citations
638. AMuSE-WSD: An All-in-one Multilingual System for Easy Word Sense DisambiguationSystem Demonstrations22 citations
639. Argument Pair Extraction with Mutual Guidance and Inter-sentence Relation GraphMain22 citations
640. Aspect-based Sentiment Analysis in Question Answering Forumsfinding22 citations
641. Back to the Basics: A Quantitative Analysis of Statistical and Graph-Based Term Weighting Schemes for Keyword ExtractionMain22 citations
642. CATE: A Contrastive Pre-trained Model for Metaphor Detection with Semi-supervised LearningMain22 citations
643. Detecting Community Sensitive Norm Violations in Online Conversationsfinding22 citations
644. Do We Know What We Don’t Know? Studying Unanswerable Questions beyond SQuAD 2.0finding22 citations
645. Efficient Multi-Task Auxiliary Learning: Selecting Auxiliary Data by Feature SimilarityMain22 citations
646. Extracting Fine-Grained Knowledge Graphs of Scientific Claims: Dataset and Transformer-Based ResultsMain22 citations
647. GAML-BERT: Improving BERT Early Exiting by Gradient Aligned Mutual LearningMain22 citations
648. Improving Abstractive Dialogue Summarization with Hierarchical Pretraining and Topic Segmentfinding22 citations
649. K-PLUG: Knowledge-injected Pre-trained Language Model for Natural Language Understanding and Generation in E-Commercefinding22 citations
650. LMdiff: A Visual Diff Tool to Compare Language ModelsSystem Demonstrations22 citations
651. Learning to Answer Psychological Questionnaire for Personality Detectionfinding22 citations
652. Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form StoriesMain22 citations
653. Micromodels for Efficient, Explainable, and Reusable Systems: A Case Study on Mental Healthfinding22 citations
654. NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Datasetfinding22 citations
655. Natural Language Processing Meets Quantum Physics: A Survey and CategorizationMain22 citations
656. Neuro-Symbolic Approaches for Text-Based Policy LearningMain22 citations
657. Not Just Classification: Recognizing Implicit Discourse Relation on Joint Modeling of Classification and GenerationMain22 citations
658. Open Knowledge Graphs Canonicalization using Variational AutoencodersMain22 citations
659. Reinforced Counterfactual Data Augmentation for Dual Sentiment ClassificationMain22 citations
660. Role of Language Relatedness in Multilingual Fine-tuning of Language Models: A Case Study in Indo-Aryan LanguagesMain22 citations
661. Rˆ3Net:Relation-embedded Representation Reconstruction Network for Change CaptioningMain22 citations
662. Salience-Aware Event Chain Modeling for Narrative UnderstandingMain22 citations
663. Sociolectal Analysis of Pretrained Language ModelsMain22 citations
664. Table-based Fact Verification With Salience-aware Learningfinding22 citations
665. Towards Realistic Few-Shot Relation ExtractionMain22 citations
666. Unsupervised Paraphrasing Consistency Training for Low Resource Named Entity RecognitionMain22 citations
667. iFacetSum: Coreference-based Interactive Faceted Summarization for Multi-Document ExplorationSystem Demonstrations22 citations
668. A Scalable Framework for Learning From Implicit User Feedback to Improve Natural Language Understanding in Large-Scale Conversational AI SystemsMain21 citations
669. APIRecX: Cross-Library API Recommendation via Pre-Trained Language ModelMain21 citations
670. Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictionsfinding21 citations
671. Beyond Reptile: Meta-Learned Dot-Product Maximization between Gradients for Improved Single-Task Regularizationfinding21 citations
672. Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese ClassificationMain21 citations
673. Detecting Frames in News Headlines and Lead Images in U.S. Gun Violence Coveragefinding21 citations
674. End-to-End Learning of Flowchart Grounded Task-Oriented DialogsMain21 citations
675. Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word SalienceMain21 citations
676. Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with IntersectionMain21 citations
677. Exploring Strategies for Generalizable Commonsense Reasoning with Pre-trained ModelsMain21 citations
678. Frame Semantic-Enhanced Sentence Modeling for Sentence-level Extractive Text SummarizationMain21 citations
679. Generalization in Text-based Games via Hierarchical Reinforcement Learningfinding21 citations
680. Geo-BERT Pre-training Model for Query Rewriting in POI Searchfinding21 citations
681. How Does Fine-tuning Affect the Geometry of Embedding Space: A Case Study on Isotropyfinding21 citations
682. Improving Query Graph Generation for Complex Question Answering over Knowledge BaseMain21 citations
683. Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer ReorderingsMain21 citations
684. Investigating Numeracy Learning Ability of a Text-to-Text Transfer Modelfinding21 citations
685. Is BERT a Cross-Disciplinary Knowledge Learner? A Surprising Finding of Pre-trained Models’ Transferabilityfinding21 citations
686. Language-agnostic Representation from Multilingual Sentence Encoders for Cross-lingual Similarity EstimationMain21 citations
687. Neural Attention-Aware Hierarchical Topic ModelMain21 citations
688. Open-domain clarification question generation without question examplesMain21 citations
689. RAST: Domain-Robust Dialogue Rewriting as Sequence TaggingMain21 citations
690. Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text RetrievalMain21 citations
691. Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddingsfinding21 citations
692. WIKIBIAS: Detecting Multi-Span Subjective Biases in Languagefinding21 citations
693. You should evaluate your language model on marginal likelihood over tokenisationsMain21 citations
694. (Mis)alignment Between Stance Expressed in Social Media Data and Public Opinion SurveysMain20 citations
695. Active Learning for Rumor Identification on Social Mediafinding20 citations
696. Are Factuality Checkers Reliable? Adversarial Meta-evaluation of Factuality in Summarizationfinding20 citations
697. CTAL: Pre-training Cross-modal Transformer for Audio-and-Language RepresentationsMain20 citations
698. Char2Subword: Extending the Subword Embedding Space Using Robust Character Compositionalityfinding20 citations
699. Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic RulesMain20 citations
700. Debiasing Methods in Natural Language Understanding Make Bias More AccessibleMain20 citations
701. Detecting Speaker Personas from Conversational TextsMain20 citations
702. Don’t be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue SystemMain20 citations
703. Fine-grained Semantic Alignment Network for Weakly Supervised Temporal Language Groundingfinding20 citations
704. Focus on what matters: Applying Discourse Coherence Theory to Cross Document CoreferenceMain20 citations
705. How May I Help You? Using Neural Text Simplification to Improve Downstream NLP Tasksfinding20 citations
706. Improving Sequence-to-Sequence Pre-training via Sequence Span RewritingMain20 citations
707. Is Information Density Uniform in Task-Oriented Dialogues?Main20 citations
708. Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learningfinding20 citations
709. Leveraging Information Bottleneck for Scientific Document Summarizationfinding20 citations
710. Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact VerificationMain20 citations
711. Neural Unification for Logic Reasoning over Natural Languagefinding20 citations
712. On the Effects of Transformer Size on In- and Out-of-Domain Calibrationfinding20 citations
713. SciXGen: A Scientific Paper Dataset for Context-Aware Text Generationfinding20 citations
714. Self Question-answering: Aspect-based Sentiment Analysis by Role Flipped Machine Reading Comprehensionfinding20 citations
715. Total Recall: a Customized Continual Learning Method for Neural Semantic ParsersMain20 citations
716. Towards Incremental Transformers: An Empirical Analysis of Transformer Models for Incremental NLUMain20 citations
717. Uncertain Local-to-Global Networks for Document-Level Event Factuality IdentificationMain20 citations
718. Understanding Politics via Contextualized Discourse ProcessingMain20 citations
719. “Was it “stated” or was it “claimed”?: How linguistic bias affects generative language modelsMain20 citations
720. A Label-Aware BERT Attention Network for Zero-Shot Multi-Intent Detection in Spoken Language UnderstandingMain19 citations
721. Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage RetrievalMain19 citations
722. Contextualize Knowledge Bases with Transformer for End-to-end Task-Oriented Dialogue SystemsMain19 citations
723. Conundrums in Event Coreference Resolution: Making Sense of the State of the ArtMain19 citations
724. Discovering Explanatory Sentences in Legal Case Decisions Using Pre-trained Language Modelsfinding19 citations
725. Don’t Go Far Off: An Empirical Study on Neural Poetry TranslationMain19 citations
726. Extracting Topics with Simultaneous Word Co-occurrence and Semantic Correlation Graphs: Neural Topic Modeling for Short Textsfinding19 citations
727. Generic resources are what you need: Style transfer tasks without task-specific parallel training dataMain19 citations
728. Knowledge Graph Representation Learning using Ordinary Differential EquationsMain19 citations
729. Learning to Ground Visual Objects for Visual Dialogfinding19 citations
730. MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answeringfinding19 citations
731. Maximal Clique Based Non-Autoregressive Open Information ExtractionMain19 citations
732. Modeling Mathematical Notation Semantics in Academic Papersfinding19 citations
733. Multilingual AMR Parsing with Noisy Knowledge Distillationfinding19 citations
734. Neural Natural Logic Inference for Interpretable Question AnsweringMain19 citations
735. PermuteFormer: Efficient Relative Position Encoding for Long SequencesMain19 citations
736. Probing Commonsense Explanation in Dialogue Response Generationfinding19 citations
737. QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer PropositionsMain19 citations
738. Scheduled Sampling Based on Decoding Steps for Neural Machine TranslationMain19 citations
739. Self-training with Few-shot RationalizationMain19 citations
740. SupCL-Seq: Supervised Contrastive Learning for Downstream Optimized Sequence Representationsfinding19 citations
741. Text Counterfactuals via Latent Optimization and Shapley-Guided SearchMain19 citations
742. Towards Making the Most of Dialogue Characteristics for Neural Chat TranslationMain19 citations
743. Transferable Persona-Grounded Dialogues via Grounded Minimal EditsMain19 citations
744. Unseen Entity Handling in Complex Question Answering over Knowledge Base via Language Generationfinding19 citations
745. YASO: A Targeted Sentiment Analysis Evaluation Dataset for Open-Domain ReviewsMain19 citations
746. AM2iCo: Evaluating Word Meaning in Context across Low-Resource Languages with Adversarial ExamplesMain18 citations
747. Adversarial Scrubbing of Demographic Information for Text ClassificationMain18 citations
748. Aligning Multidimensional Worldviews and Discovering Ideological DifferencesMain18 citations
749. Bandits Don’t Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Banditsfinding18 citations
750. Beyond Text: Incorporating Metadata and Label Structure for Multi-Label Document Classification using Heterogeneous GraphsMain18 citations
751. Certified Robustness to Programmable Transformations in LSTMsMain18 citations
752. Cross-lingual Intermediate Fine-tuning improves Dialogue State TrackingMain18 citations
753. DomiKnowS: A Library for Integration of Symbolic Domain Knowledge in Deep LearningSystem Demonstrations18 citations
754. Exploring a Unified Sequence-To-Sequence Transformer for Medical Product Safety Monitoring in Social Mediafinding18 citations
755. How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?finding18 citations
756. IGA: An Intent-Guided Authoring AssistantMain18 citations
757. Inflate and Shrink:Enriching and Reducing Interactions for Fast Text-Image RetrievalMain18 citations
758. Putting Words in BERT’s Mouth: Navigating Contextualized Vector Spaces with PseudowordsMain18 citations
759. RankNAS: Efficient Neural Architecture Search by Pairwise RankingMain18 citations
760. Robustness Evaluation of Entity Disambiguation Using Prior Probes: the Case of Entity OvershadowingMain18 citations
761. Self-Supervised Curriculum Learning for Spelling Error CorrectionMain18 citations
762. Semi-Supervised Exaggeration Detection of Health Science Press ReleasesMain18 citations
763. Synchronous Dual Network with Cross-Type Attention for Joint Entity and Relation ExtractionMain18 citations
764. Unsupervised Relation Extraction: A Variational Autoencoder ApproachMain18 citations
765. Adapting Entities across Languages and Culturesfinding17 citations
766. Adversarial Attack against Cross-lingual Knowledge Graph AlignmentMain17 citations
767. COUGH: A Challenge Dataset and Models for COVID-19 FAQ RetrievalMain17 citations
768. Enlivening Redundant Heads in Multi-head Self-attention for Machine TranslationMain17 citations
769. GMH: A General Multi-hop Reasoning Model for KG CompletionMain17 citations
770. GeneSis: A Generative Approach to Substitutes in ContextMain17 citations
771. Mixup Decoding for Diverse Machine Translationfinding17 citations
772. Multivalent Entailment Graphs for Question AnsweringMain17 citations
773. NDH-Full: Learning and Evaluating Navigational Agents on Full-Length DialogueMain17 citations
774. Open-Domain Question-Answering for COVID-19 and Other Emergent DomainsSystem Demonstrations17 citations
775. QACE: Asking Questions to Evaluate an Image Captionfinding17 citations
776. Self-Supervised Detection of Contextual Synonyms in a Multi-Class Setting: Phenotype Annotation Use CaseMain17 citations
777. Simple or Complex? Complexity-controllable Question Generation with Soft Templates and Deep Mixture of Experts Modelfinding17 citations
778. Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading ComprehensionMain17 citations
779. Unsupervised Multi-View Post-OCR Error Correction With Language ModelsMain17 citations
780. mDAPT: Multilingual Domain Adaptive Pretraining in a Single Modelfinding17 citations
781. An Empirical Study on Multiple Information Sources for Zero-Shot Fine-Grained Entity TypingMain16 citations
782. An Information-Theoretic Characterization of Morphological FusionMain16 citations
783. Boosting Cross-Lingual Transfer via Self-Learning with Uncertainty EstimationMain16 citations
784. Context-Aware Interaction Network for Question MatchingMain16 citations
785. Controlled Neural Sentence-Level Reframing of News Articlesfinding16 citations
786. Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation NetworksMain16 citations
787. Grammatical Error Correction with Contrastive Learning in Low Error Density Domainsfinding16 citations
788. Is this the end of the gold standard? A straightforward reference-less grammatical error correction metricMain16 citations
789. Linguistic Dependencies and Statistical DependenceMain16 citations
790. Mining the Cause of Political Decision-Making from Social Media: A Case Study of COVID-19 Policies across the US Statesfinding16 citations
791. Multi-Vector Attention Models for Deep Re-rankingMain16 citations
792. Nearest Neighbour Few-Shot Learning for Cross-lingual ClassificationMain16 citations
793. NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge BasesMain16 citations
794. PRIDE: Predicting Relationships in ConversationsMain16 citations
795. PhoMT: A High-Quality and Large-Scale Benchmark Dataset for Vietnamese-English Machine TranslationMain16 citations
796. Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Frameworkfinding16 citations
797. SPARQLing Database Queries from Intermediate Question DecompositionsMain16 citations
798. Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog SystemsMain16 citations
799. Sequential Cross-Document Coreference ResolutionMain16 citations
800. Set Generation Networks for End-to-End Knowledge Base PopulationMain16 citations
801. Smelting Gold and Silver for Improved Multilingual AMR-to-Text GenerationMain16 citations
802. Structure-Augmented Keyphrase GenerationMain16 citations
803. Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillationfinding16 citations
804. Towards Document-Level Paraphrase Generation with Sentence Rewriting and Reorderingfinding16 citations
805. Treasures Outside Contexts: Improving Event Detection via Global StatisticsMain16 citations
806. Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation TrainingMain16 citations
807. When in Doubt: Improving Classification Performance with Alternating Normalizationfinding16 citations
808. #HowYouTagTweets: Learning User Hashtagging Preferences via Personalized Topic AttentionMain15 citations
809. Automatically Exposing Problems with Neural Dialog ModelsMain15 citations
810. Box Embeddings: An open-source library for representation learning using geometric structuresSystem Demonstrations15 citations
811. Chandler: An Explainable Sarcastic Response GeneratorSystem Demonstrations15 citations
812. Competence-based Curriculum Learning for Multilingual Machine Translationfinding15 citations
813. Constructing a Psychometric Testbed for Fair Natural Language ProcessingMain15 citations
814. Cryptonite: A Cryptic Crossword Benchmark for Extreme Ambiguity in LanguageMain15 citations
815. Decision-Focused SummarizationMain15 citations
816. Dynamic Forecasting of Conversation DerailmentMain15 citations
817. EARL: Informative Knowledge-Grounded Conversation Generation with Entity-Agnostic Representation LearningMain15 citations
818. Emotion Inference in Multi-Turn Conversations with Addressee-Aware Module and Ensemble StrategyMain15 citations
819. End-to-End Conversational Search for Online Shopping with Utterance TransferMain15 citations
820. Graphine: A Dataset for Graph-aware Terminology Definition GenerationMain15 citations
821. HypMix: Hyperbolic Interpolative Data AugmentationMain15 citations
822. IR like a SIR: Sense-enhanced Information Retrieval for Multiple LanguagesMain15 citations
823. Implicit Premise Generation with Discourse-aware Commonsense Knowledge ModelsMain15 citations
824. Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise OrderingsMain15 citations
825. InVeRo-XL: Making Cross-Lingual Semantic Role Labeling Accessible with Intelligible Verbs and RolesSystem Demonstrations15 citations
826. Knowledge-Enhanced Evidence Retrieval for Counterargument Generationfinding15 citations
827. Leveraging Word-Formation Knowledge for Chinese Word Sense Disambiguationfinding15 citations
828. Meta-LMTC: Meta-Learning for Large-Scale Multi-Label Text ClassificationMain15 citations
829. MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity RepresentationsMain15 citations
830. Multi-Task Dense Retrieval via Model Uncertainty Fusion for Open-Domain Question Answeringfinding15 citations
831. Numerical reasoning in machine reading comprehension tasks: are we there yet?Main15 citations
832. On Classifying whether Two Texts are on the Same Side of an ArgumentMain15 citations
833. OpenFraming: Open-sourced Tool for Computational Framing Analysis of Multilingual DataSystem Demonstrations15 citations
834. Point-of-Interest Type Prediction using Text and ImagesMain15 citations
835. Re-embedding Difficult Samples via Mutual Information Constrained Semantically Oversampling for Imbalanced Text ClassificationMain15 citations
836. Reconstruction Attack on Instance Encoding for Language UnderstandingMain15 citations
837. Sometimes We Want Ungrammatical Translationsfinding15 citations
838. Style Pooling: Automatic Text Style Obfuscation for Improved Classification FairnessMain15 citations
839. TEBNER: Domain Specific Named Entity Recognition with Type Expanded Boundary-aware NetworkMain15 citations
840. Transformer-based Lexically Constrained Headline GenerationMain15 citations
841. A Finer-grain Universal Dialogue Semantic Structures based Model For Abstractive Dialogue Summarizationfinding14 citations
842. Analysis of Language Change in Collaborative Instruction Followingfinding14 citations
843. COSMic: A Coherence-Aware Generation Metric for Image Descriptionsfinding14 citations
844. Contrastive Representation Learning for Exemplar-Guided Paraphrase Generationfinding14 citations
845. Finnish Dialect Identification: The Effect of Audio and TextMain14 citations
846. GupShup: Summarizing Open-Domain Code-Switched ConversationsMain14 citations
847. HiTRANS: A Hierarchical Transformer Network for Nested Named Entity Recognitionfinding14 citations
848. Inducing Stereotypical Character Roles from Plot StructureMain14 citations
849. Japanese Zero Anaphora Resolution Can Benefit from Parallel Texts Through Neural Transfer Learningfinding14 citations
850. Language Clustering for Multilingual Named Entity Recognitionfinding14 citations
851. Learn to Copy from the Copying History: Correlational Copy Network for Abstractive SummarizationMain14 citations
852. Looking for Confirmations: An Effective and Human-Like Visual Dialogue StrategyMain14 citations
853. MetaTS: Meta Teacher-Student Network for Multilingual Sequence Labeling with Minimal SupervisionMain14 citations
854. Modeling Human Sentence Processing with Left-Corner Recurrent Neural Network GrammarsMain14 citations
855. Multi-task Learning to Enable Location Mention Identification in the Early Hours of a Crisis Eventfinding14 citations
856. Novel Natural Language Summarization of Program Code via Leveraging Multiple Input Representationsfinding14 citations
857. Pseudo Zero Pronoun Resolution Improves Zero Anaphora ResolutionMain14 citations
858. Self-Supervised Quality Estimation for Machine TranslationMain14 citations
859. Semantic Novelty Detection in Natural Language DescriptionsMain14 citations
860. Sent2Span: Span Detection for PICO Extraction in the Biomedical Text without Span Annotationsfinding14 citations
861. Sentence-Permuted Paragraph GenerationMain14 citations
862. SummerTime: Text Summarization Toolkit for Non-expertsSystem Demonstrations14 citations
863. Task-adaptive Pre-training and Self-training are Complementary for Natural Language Understandingfinding14 citations
864. Translation-based Supervision for Policy Generation in Simultaneous Neural Machine TranslationMain14 citations
865. Wine is not v i n. On the Compatibility of Tokenizations across Languagesfinding14 citations
866. WinoLogic: A Zero-Shot Logic-based Diagnostic Dataset for Winograd Schema ChallengeMain14 citations
867. XLEnt: Mining a Large Cross-lingual Entity Dataset with Lexical-Semantic-Phonetic Word AlignmentMain14 citations
868. A Language Model-based Generative Classifier for Sentence-level Discourse ParsingMain13 citations
869. An Empirical Investigation of Word Alignment Supervision for Zero-Shot Multilingual Neural Machine TranslationMain13 citations
870. CVAE-based Re-anchoring for Implicit Discourse Relation Classificationfinding13 citations
871. Constructing contrastive samples via summarization for text classification with limited annotationsfinding13 citations
872. Detecting Polarized Topics Using Partisanship-aware Contextualized Topic Embeddingsfinding13 citations
873. Distantly Supervised Relation Extraction in Federated Settingsfinding13 citations
874. Distantly Supervised Relation Extraction using Multi-Layer Revision Network and Confidence-based Multi-Instance LearningMain13 citations
875. Does It Capture STEL? A Modular, Similarity-based Linguistic Style Evaluation FrameworkMain13 citations
876. Efficient Dialogue Complementary Policy Learning via Deep Q-network Policy and Episodic Memory PolicyMain13 citations
877. Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesserfinding13 citations
878. ExcavatorCovid: Extracting Events and Relations from Text Corpora for Temporal and Causal Analysis for COVID-19System Demonstrations13 citations
879. Foreseeing the Benefits of Incidental SupervisionMain13 citations
880. Improving Pre-trained Vision-and-Language Embeddings for Phrase GroundingMain13 citations
881. Incorporating Circumstances into Narrative Event Predictionfinding13 citations
882. Knowledge-Guided Paraphrase Identificationfinding13 citations
883. Open-Domain Contextual Link Prediction and its Complementarity with Entailment Graphsfinding13 citations
884. Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transferfinding13 citations
885. Retrieve, Discriminate and Rewrite: A Simple and Effective Framework for Obtaining Affective Response in Retrieval-Based Chatbotsfinding13 citations
886. STaCK: Sentence Ordering with Temporal Commonsense KnowledgeMain13 citations
887. Sequential Randomized Smoothing for Adversarially Robust Speech RecognitionMain13 citations
888. Studying word order through iterative shufflingMain13 citations
889. TWT: Table with Written Text for Controlled Data-to-Text Generationfinding13 citations
890. Thermostat: A Large Collection of NLP Model Explanations and Analysis ToolsSystem Demonstrations13 citations
891. To Share or not to Share: Predicting Sets of Sources for Model Transfer LearningMain13 citations
892. Uncertainty Measures in Neural Belief Tracking and the Effects on Dialogue Policy PerformanceMain13 citations
893. WhyAct: Identifying Action Reasons in Lifestyle VlogsMain13 citations
894. A Collaborative Multi-agent Reinforcement Learning Framework for Dialog Action DecompositionMain12 citations
895. A Differentiable Relaxation of Graph Segmentation and Alignment for AMR ParsingMain12 citations
896. A Graph-Based Neural Model for End-to-End Frame Semantic ParsingMain12 citations
897. A Pretraining Numerical Reasoning Model for Ordinal Constrained Question Answering on Knowledge Basefinding12 citations
898. A Semantic Filter Based on Relations for Knowledge Graph CompletionMain12 citations
899. A multilabel approach to morphosyntactic probingfinding12 citations
900. An unsupervised framework for tracing textual sources of moral changefinding12 citations
901. Athena 2.0: Contextualized Dialogue Management for an Alexa Prize SocialBotSystem Demonstrations12 citations
902. Beyond Grammatical Error Correction: Improving L1-influenced research writing in English using pre-trained encoder-decoder modelsfinding12 citations
903. Conditional Poisson Stochastic BeamsMain12 citations
904. Continual Few-Shot Learning for Text ClassificationMain12 citations
905. Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text ClassificationMain12 citations
906. DIRECT: Direct and Indirect Responses in Conversational Text Corpusfinding12 citations
907. Discovering Representation Sprachbund For Multilingual Pre-Trainingfinding12 citations
908. Distantly-Supervised Dense Retrieval Enables Open-Domain Question Answering without Evidence AnnotationMain12 citations
909. Efficient Inference for Multilingual Neural Machine TranslationMain12 citations
910. Enhancing Dual-Encoders with Question and Answer Cross-Embeddings for Answer Retrievalfinding12 citations
911. Entity-level Cross-modal Learning Improves Multi-modal Machine Translationfinding12 citations
912. Exploring Multitask Learning for Low-Resource Abstractive Summarizationfinding12 citations
913. GFST: Gender-Filtered Self-Training for More Accurate Gender in TranslationMain12 citations
914. GenerativeRE: Incorporating a Novel Copy Mechanism and Pretrained Model for Joint Entity and Relation Extractionfinding12 citations
915. Give the Truth: Incorporate Semantic Slot into Abstractive Dialogue Summarizationfinding12 citations
916. Glyph Enhanced Chinese Character Pre-Training for Lexical Sememe Predictionfinding12 citations
917. LMSOC: An Approach for Socially Sensitive Pretrainingfinding12 citations
918. Learning Numeracy: A Simple Yet Effective Number Embedding Approach Using Knowledge Graphfinding12 citations
919. Mapping probability word problems to executable representationsMain12 citations
920. NB-MLM: Efficient Domain Adaptation of Masked Language Models for Sentiment AnalysisMain12 citations
921. On the Influence of Masking Policies in Intermediate Pre-trainingMain12 citations
922. Paired Examples as Indirect Supervision in Latent Decision ModelsMain12 citations
923. Probing Pre-trained Language Models for Semantic Attributes and their Valuesfinding12 citations
924. SYSML: StYlometry with Structure and Multitask Learning: Implications for Darknet Forum Migrant AnalysisMain12 citations
925. Self-Supervised Neural Topic Modelingfinding12 citations
926. Stream-level Latency Evaluation for Simultaneous Machine Translationfinding12 citations
927. Summary Explorer: Visualizing the State of the Art in Text SummarizationSystem Demonstrations12 citations
928. Topic Transferable Table Question AnsweringMain12 citations
929. Bayesian Topic Regression for Causal InferenceMain11 citations
930. CHoRaL: Collecting Humor Reaction Labels from Millions of Social Media UsersMain11 citations
931. CoPHE: A Count-Preserving Hierarchical Evaluation Metric in Large-Scale Multi-Label Text ClassificationMain11 citations
932. Detect and Classify – Joint Span Detection and Classification for Health OutcomesMain11 citations
933. Detecting Compositionally Out-of-Distribution Examples in Semantic Parsingfinding11 citations
934. ET: A Workstation for Querying, Editing and Evaluating Annotated CorporaSystem Demonstrations11 citations
935. Evaluation Paradigms in Question AnsweringMain11 citations
936. Explore Better Relative Position Embeddings from Encoding Perspective for Transformer ModelsMain11 citations
937. Fine-grained Factual Consistency Assessment for Abstractive Summarization ModelsMain11 citations
938. Generation and Extraction Combined Dialogue State Tracking with Hierarchical Ontology IntegrationMain11 citations
939. Grounded Graph Decoding improves Compositional Generalization in Question Answeringfinding11 citations
940. Learning with Instance Bundles for Reading ComprehensionMain11 citations
941. MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarizationfinding11 citations
942. Mind the Context: The Impact of Contextualization in Neural Module Networks for Grounding Visual Referring ExpressionsMain11 citations
943. Model Selection for Cross-lingual TransferMain11 citations
944. Modeling Users and Online Communities for Abuse Detection: A Position on Ethics and Explainabilityfinding11 citations
945. On the Challenges of Evaluating Compositional Explanations in Multi-Hop Inference: Relevance, Completeness, and Expert RatingsMain11 citations
946. Profiling News Discourse Structure Using Explicit Subtopic Structures Guided Criticsfinding11 citations
947. RW-KD: Sample-wise Loss Terms Re-Weighting for Knowledge Distillationfinding11 citations
948. Recurrent Attention for Neural Machine TranslationMain11 citations
949. Structured abbreviation expansion in contextfinding11 citations
950. Towards Automatic Bias Detection in Knowledge Graphsfinding11 citations
951. Towards Label-Agnostic Emotion EmbeddingsMain11 citations
952. Winnowing Knowledge for Multi-choice Question Answeringfinding11 citations
953. A Massively Multilingual Analysis of Cross-linguality in Shared Embedding SpaceMain10 citations
954. A Neural Graph-based Local Coherence Modelfinding10 citations
955. Adversarial Regularization as Stackelberg Game: An Unrolled Optimization ApproachMain10 citations
956. Analyzing the Surprising Variability in Word Embedding Stability Across LanguagesMain10 citations
957. Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shotsfinding10 citations
958. Automatic rule generation for time expression normalizationfinding10 citations
959. Calibrate your listeners! Robust communication-based training for pragmatic speakersfinding10 citations
960. ClauseRec: A Clause Recommendation Framework for AI-aided Contract AuthoringMain10 citations
961. Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense InventoriesMain10 citations
962. Coupling Context Modeling with Zero Pronoun Recovering for Document-Level Natural Language GenerationMain10 citations
963. DRIFT: A Toolkit for Diachronic Analysis of Scientific LiteratureSystem Demonstrations10 citations
964. Detecting Health Advice in Medical Research LiteratureMain10 citations
965. Effective Fine-Tuning Methods for Cross-lingual AdaptationMain10 citations
966. Evaluating the Morphosyntactic Well-formedness of Generated TextsMain10 citations
967. Exploiting Curriculum Learning in Unsupervised Neural Machine Translationfinding10 citations
968. Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data SelectionMain10 citations
969. GraphMR: Graph Neural Network for Mathematical ReasoningMain10 citations
970. Improved Latent Tree Induction with Distant Supervision via Span ConstraintsMain10 citations
971. Improving Knowledge Graph Embedding Using Affine Transformations of Entities Corresponding to Each Relationfinding10 citations
972. Instance-adaptive training with noise-robust losses against noisy labelsMain10 citations
973. Integrating Personalized PageRank into Neural Word Sense DisambiguationMain10 citations
974. Lexicon-Based Graph Convolutional Network for Chinese Word Segmentationfinding10 citations
975. Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax HierarchyMain10 citations
976. Low-Rank Subspaces for Unsupervised Entity LinkingMain10 citations
977. Mitigating Data Poisoning in Text Classification with Differential Privacyfinding10 citations
978. Modular Self-Supervision for Document-Level Relation ExtractionMain10 citations
979. Perhaps PTLMs Should Go to School – A Task to Assess Open Book and Closed Book QAMain10 citations
980. Revisiting Robust Neural Machine Translation: A Transformer Case Studyfinding10 citations
981. SPRING Goes Online: End-to-End AMR Parsing and GenerationSystem Demonstrations10 citations
982. Skim-Attention: Learning to Focus via Document Layoutfinding10 citations
983. Subword Mapping and Anchoring across Languagesfinding10 citations
984. Using Sociolinguistic Variables to Reveal Changing Attitudes Towards Sexuality and GenderMain10 citations
985. What’s in Your Head? Emergent Behaviour in Multi-Task Transformer ModelsMain10 citations
986. kFolden: k-Fold Ensemble for Out-Of-Distribution DetectionMain10 citations
987. Augmenting BERT-style Models with Predictive Coding to Improve Discourse-level RepresentationsMain9 citations
988. Building Adaptive Acceptability Classifiers for Neural NLGMain9 citations
989. CNNBiF: CNN-based Bigram Features for Named Entity Recognitionfinding9 citations
990. CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role LabelingMain9 citations
991. Can We Improve Model Robustness through Secondary Attribute Counterfactuals?Main9 citations
992. Contextual Rephrase Detection for Reducing Friction in Dialogue SystemsMain9 citations
993. Data-to-text Generation by Splicing Together Nearest NeighborsMain9 citations
994. Diversity and Consistency: Exploring Visual Question-Answer Pair Generationfinding9 citations
995. Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical InterpretationsMain9 citations
996. Enhancing the Context Representation in Similarity-based Word Sense DisambiguationMain9 citations
997. Entity-Based Semantic Adequacy for Data-to-Text Generationfinding9 citations
998. Event Graph based Sentence FusionMain9 citations
999. Exploiting Twitter as Source of Large Corpora of Weakly Similar Pairs for Semantic Sentence EmbeddingsMain9 citations
1000. Extract, Integrate, Compete: Towards Verification Style Reading Comprehensionfinding9 citations

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