NAACL 2021 Accepted Papers

The full list of 533 papers accepted at NAACL 2021 (North American Chapter of the Association for Computational Linguistics). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

1. mT5: A Massively Multilingual Pre-trained Text-to-Text TransformerLong2,724 citations
2. It’s Not Just Size That Matters: Small Language Models Are Also Few-Shot LearnersLong1,036 citations
3. Unified Pre-training for Program Understanding and GenerationLong924 citations
4. Are NLP Models really able to Solve Simple Math Word Problems?Long779 citations
5. QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question AnsweringLong689 citations
6. RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question AnsweringLong664 citations
7. A Frustratingly Easy Approach for Entity and Relation ExtractionLong603 citations
8. KILT: a Benchmark for Knowledge Intensive Language TasksLong590 citations
9. Learning How to Ask: Querying LMs with Mixtures of Soft PromptsLong590 citations
10. Dynabench: Rethinking Benchmarking in NLPLong471 citations
11. Factual Probing Is [MASK]: Learning vs. Learning to RecallLong427 citations
12. A Survey on Recent Approaches for Natural Language Processing in Low-Resource ScenariosLong393 citations
13. InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-TrainingLong371 citations
14. Self-Alignment Pretraining for Biomedical Entity RepresentationsLong371 citations
15. FUDGE: Controlled Text Generation With Future DiscriminatorsLong342 citations
16. QMSum: A New Benchmark for Query-based Multi-domain Meeting SummarizationLong341 citations
17. Document-Level Event Argument Extraction by Conditional GenerationLong334 citations
18. Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality MetricsLong321 citations
19. How many data points is a prompt worth?Long320 citations
20. Efficient Attentions for Long Document SummarizationLong303 citations
21. A Dataset of Information-Seeking Questions and Answers Anchored in Research PapersLong296 citations
22. Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring TasksLong296 citations
23. GSum: A General Framework for Guided Neural Abstractive SummarizationLong284 citations
24. Contextualized Perturbation for Textual Adversarial AttackLong275 citations
25. COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted ListLong260 citations
26. Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-trainingLong247 citations
27. Supporting Clustering with Contrastive LearningLong247 citations
28. Get Your Vitamin C! Robust Fact Verification with Contrastive EvidenceLong242 citations
29. The Curious Case of Hallucinations in Neural Machine TranslationLong225 citations
30. The Importance of Modeling Social Factors of Language: Theory and PracticeLong208 citations
31. DART: Open-Domain Structured Data Record to Text GenerationLong200 citations
32. TABBIE: Pretrained Representations of Tabular DataLong200 citations
33. Hurdles to Progress in Long-form Question AnsweringLong199 citations
34. Concealed Data Poisoning Attacks on NLP ModelsLong196 citations
35. Aspect-based Sentiment Analysis with Type-aware Graph Convolutional Networks and Layer EnsembleLong195 citations
36. Improving Factual Completeness and Consistency of Image-to-Text Radiology Report GenerationLong195 citations
37. Open-Domain Question Answering Goes Conversational via Question RewritingLong190 citations
38. What Will it Take to Fix Benchmarking in Natural Language Understanding?Long189 citations
39. Enhancing Factual Consistency of Abstractive SummarizationLong185 citations
40. Self-training Improves Pre-training for Natural Language UnderstandingLong183 citations
41. Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTaLong181 citations
42. HONEST: Measuring Hurtful Sentence Completion in Language ModelsLong179 citations
43. Structure-Grounded Pretraining for Text-to-SQLLong172 citations
44. Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP ModelsLong171 citations
45. Bot-Adversarial Dialogue for Safe Conversational AgentsLong165 citations
46. COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report GenerationSystem Demonstrations165 citations
47. NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic ConstraintsLong165 citations
48. Annotating and Modeling Fine-grained Factuality in SummarizationLong162 citations
49. XOR QA: Cross-lingual Open-Retrieval Question AnsweringLong161 citations
50. SmBoP: Semi-autoregressive Bottom-up Semantic ParsingLong158 citations
51. UmlsBERT: Clinical Domain Knowledge Augmentation of Contextual Embeddings Using the Unified Medical Language System MetathesaurusLong157 citations
52. MediaSum: A Large-scale Media Interview Dataset for Dialogue SummarizationLong153 citations
53. When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language ModelsLong153 citations
54. Robustness Gym: Unifying the NLP Evaluation LandscapeSystem Demonstrations152 citations
55. Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training ApproachLong148 citations
56. Detoxifying Language Models Risks Marginalizing Minority VoicesLong147 citations
57. Representing Numbers in NLP: a Survey and a VisionLong133 citations
58. Beyond Black & White: Leveraging Annotator Disagreement via Soft-Label Multi-Task LearningLong132 citations
59. Paragraph-level Simplification of Medical TextsLong129 citations
60. Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?Long126 citations
61. Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights CasesLong126 citations
62. Temporal Knowledge Graph Completion using a Linear Temporal Regularizer and Multivector EmbeddingsLong126 citations
63. Controllable Text Simplification with Explicit ParaphrasingLong120 citations
64. Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and SelectionLong118 citations
65. Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data AugmentationLong117 citations
66. Open Domain Question Answering over Tables via Dense RetrievalLong113 citations
67. Introducing CAD: the Contextual Abuse DatasetLong112 citations
68. Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!Long112 citations
69. Knowledge Enhanced Masked Language Model for Stance DetectionLong111 citations
70. MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification TheoriesLong110 citations
71. Beyond Fair Pay: Ethical Implications of NLP CrowdsourcingLong109 citations
72. Continual Learning for Text Classification with Information Disentanglement Based RegularizationLong109 citations
73. ESC: Redesigning WSD with Extractive Sense ComprehensionLong109 citations
74. Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU modelsLong107 citations
75. Adversarial Learning for Zero-Shot Stance Detection on Social MediaLong106 citations
76. Modeling Framing in Immigration Discourse on Social MediaLong103 citations
77. Progressive Generation of Long Text with Pretrained Language ModelsLong103 citations
78. Self-Training with Weak SupervisionLong102 citations
79. Structure-Aware Abstractive Conversation Summarization via Discourse and Action GraphsLong101 citations
80. Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue StateTrackingLong100 citations
81. AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive SummarizationLong99 citations
82. MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language SequencesLong99 citations
83. Abstract Meaning Representation Guided Graph Encoding and Decoding for Joint Information ExtractionLong97 citations
84. LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text RetrievalLong97 citations
85. Understanding by Understanding Not: Modeling Negation in Language ModelsLong96 citations
86. ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation LearningLong96 citations
87. Text Modular Networks: Learning to Decompose Tasks in the Language of Existing ModelsLong94 citations
88. X-Class: Text Classification with Extremely Weak SupervisionLong94 citations
89. SPARTQA: A Textual Question Answering Benchmark for Spatial ReasoningLong93 citations
90. SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching RetrievalLong92 citations
91. Universal Adversarial Attacks with Natural Triggers for Text ClassificationLong92 citations
92. Towards Few-shot Fact-Checking via PerplexityLong91 citations
93. Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge GraphLong90 citations
94. Topic Model or Topic Twaddle? Re-evaluating Semantic Interpretability MeasuresLong90 citations
95. Adding Chit-Chat to Enhance Task-Oriented DialoguesLong89 citations
96. Meta-Learning for Domain Generalization in Semantic ParsingLong89 citations
97. Fine-grained Post-training for Improving Retrieval-based Dialogue SystemsLong88 citations
98. Multimodal End-to-End Sparse Model for Emotion RecognitionLong87 citations
99. Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification TasksLong86 citations
100. Mask Attention Networks: Rethinking and Strengthen TransformerLong83 citations
101. Temporal Reasoning on Implicit Events from Distant SupervisionLong83 citations
102. HTCInfoMax: A Global Model for Hierarchical Text Classification via Information MaximizationLong82 citations
103. Scalable and Interpretable Semantic Change DetectionLong82 citations
104. ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating PredictionLong81 citations
105. Aspect-Controlled Neural Argument GenerationLong81 citations
106. On Transferability of Bias Mitigation Effects in Language Model Fine-TuningLong81 citations
107. SPLAT: Speech-Language Joint Pre-Training for Spoken Language UnderstandingLong81 citations
108. Implicitly Abusive Language – What does it actually look like and why are we not getting there?Long79 citations
109. Towards a Comprehensive Understanding and Accurate Evaluation of Societal Biases in Pre-Trained TransformersLong78 citations
110. Graph Convolutional Networks for Event Causality Identification with Rich Document-level StructuresLong77 citations
111. LightSeq: A High Performance Inference Library for TransformersIndustry77 citations
112. MERMAID: Metaphor Generation with Symbolism and Discriminative DecodingLong77 citations
113. TaxoClass: Hierarchical Multi-Label Text Classification Using Only Class NamesLong77 citations
114. Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue SystemsLong76 citations
115. Limitations of Autoregressive Models and Their AlternativesLong76 citations
116. Measuring Social Biases in Grounded Vision and Language EmbeddingsLong76 citations
117. Cross-Task Instance Representation Interactions and Label Dependencies for Joint Information Extraction with Graph Convolutional NetworksLong75 citations
118. Grey-box Adversarial Attack And Defence For Sentiment ClassificationLong75 citations
119. Efficiently Summarizing Text and Graph Encodings of Multi-Document ClustersLong74 citations
120. UDALM: Unsupervised Domain Adaptation through Language ModelingLong73 citations
121. Adaptable and Interpretable Neural MemoryOver Symbolic KnowledgeLong72 citations
122. GEMNET: Effective Gated Gazetteer Representations for Recognizing Complex Entities in Low-context InputLong72 citations
123. Clustering-based Inference for Biomedical Entity LinkingLong70 citations
124. Personalized Response Generation via Generative Split Memory NetworkLong70 citations
125. Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum LearningLong69 citations
126. Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language ModelsLong69 citations
127. DeCEMBERT: Learning from Noisy Instructional Videos via Dense Captions and Entropy MinimizationLong68 citations
128. TR-BERT: Dynamic Token Reduction for Accelerating BERT InferenceLong68 citations
129. Noisy-Labeled NER with Confidence EstimationLong67 citations
130. DAGN: Discourse-Aware Graph Network for Logical ReasoningLong66 citations
131. Unsupervised Multi-hop Question Answering by Question GenerationLong66 citations
132. Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment ClassificationLong65 citations
133. Industry Scale Semi-Supervised Learning for Natural Language UnderstandingIndustry65 citations
134. On the Transformer Growth for Progressive BERT TrainingLong65 citations
135. RESIN: A Dockerized Schema-Guided Cross-document Cross-lingual Cross-media Information Extraction and Event Tracking SystemSystem Demonstrations65 citations
136. Align-Refine: Non-Autoregressive Speech Recognition via Iterative RealignmentLong64 citations
137. Evaluating Saliency Methods for Neural Language ModelsLong64 citations
138. Compositional Generalization for Neural Semantic Parsing via Span-level Supervised AttentionLong63 citations
139. Rethinking Network Pruning – under the Pre-train and Fine-tune ParadigmLong63 citations
140. WRIME: A New Dataset for Emotional Intensity Estimation with Subjective and Objective AnnotationsLong62 citations
141. Causal Effects of Linguistic PropertiesLong61 citations
142. Counterfactual Data Augmentation for Neural Machine TranslationLong60 citations
143. Few-shot Intent Classification and Slot Filling with Retrieved ExamplesLong60 citations
144. How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy WorldsLong59 citations
145. Improving Generation and Evaluation of Visual Stories via Semantic ConsistencyLong59 citations
146. “Nice Try, Kiddo”: Investigating Ad Hominems in Dialogue ResponsesLong59 citations
147. Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and SystemLong58 citations
148. Looking Beyond Sentence-Level Natural Language Inference for Question Answering and Text SummarizationLong58 citations
149. Noisy Self-Knowledge Distillation for Text SummarizationLong58 citations
150. On Attention Redundancy: A Comprehensive StudyLong58 citations
151. ShadowGNN: Graph Projection Neural Network for Text-to-SQL ParserLong58 citations
152. AMR Parsing with Action-Pointer TransformerLong57 citations
153. Learning to Synthesize Data for Semantic ParsingLong57 citations
154. Multilingual Language Models Predict Human Reading BehaviorLong57 citations
155. Probabilistic Box Embeddings for Uncertain Knowledge Graph ReasoningLong57 citations
156. Emotion-Infused Models for Explainable Psychological Stress DetectionLong56 citations
157. Low-Complexity Probing via Finding SubnetworksLong56 citations
158. Suicide Ideation Detection via Social and Temporal User Representations using Hyperbolic LearningLong56 citations
159. Understanding Hard Negatives in Noise Contrastive EstimationLong55 citations
160. What’s in a Summary? Laying the Groundwork for Advances in Hospital-Course SummarizationLong54 citations
161. CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation SystemsLong53 citations
162. Discourse Probing of Pretrained Language ModelsLong53 citations
163. ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language UnderstandingLong53 citations
164. Olá, Bonjour, Salve! XFORMAL: A Benchmark for Multilingual Formality Style TransferLong53 citations
165. Sliding Selector Network with Dynamic Memory for Extractive Summarization of Long DocumentsLong53 citations
166. A Global Past-Future Early Exit Method for Accelerating Inference of Pre-trained Language ModelsLong52 citations
167. An Empirical Study on Neural Keyphrase GenerationLong52 citations
168. Domain Divergences: A Survey and Empirical AnalysisLong52 citations
169. ER-AE: Differentially Private Text Generation for Authorship AnonymizationLong52 citations
170. Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language ModelLong52 citations
171. Multi-view Subword RegularizationLong52 citations
172. Recent advances in neural metaphor processing: A linguistic, cognitive and social perspectiveLong52 citations
173. Revisiting the Weaknesses of Reinforcement Learning for Neural Machine TranslationLong52 citations
174. Ask what’s missing and what’s useful: Improving Clarification Question Generation using Global KnowledgeLong51 citations
175. Explicit Alignment Objectives for Multilingual Bidirectional EncodersLong50 citations
176. Learning to Recognize Dialect FeaturesLong50 citations
177. StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style TransferLong50 citations
178. Grounding Open-Domain Instructions to Automate Web Support TasksLong49 citations
179. NL-EDIT: Correcting Semantic Parse Errors through Natural Language InteractionLong49 citations
180. Refining Targeted Syntactic Evaluation of Language ModelsLong49 citations
181. Certified Robustness to Word Substitution Attack with Differential PrivacyLong48 citations
182. Controlling Dialogue Generation with Semantic ExemplarsLong47 citations
183. Empirical Evaluation of Pre-trained Transformers for Human-Level NLP: The Role of Sample Size and DimensionalityLong47 citations
184. Source and Target Bidirectional Knowledge Distillation for End-to-end Speech TranslationLong47 citations
185. Generative Imagination Elevates Machine TranslationLong46 citations
186. On Learning Text Style Transfer with Direct RewardsLong46 citations
187. Multilingual BERT Post-Pretraining AlignmentLong45 citations
188. Noise Stability Regularization for Improving BERT Fine-tuningLong45 citations
189. Rethinking Perturbations in Encoder-Decoders for Fast TrainingLong45 citations
190. D2S: Document-to-Slide Generation Via Query-Based Text SummarizationLong44 citations
191. Differentiable Open-Ended Commonsense ReasoningLong44 citations
192. Example-Driven Intent Prediction with ObserversLong44 citations
193. Focused Attention Improves Document-Grounded GenerationLong44 citations
194. Fool Me Twice: Entailment from Wikipedia GamificationLong44 citations
195. Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic InformationLong44 citations
196. MUDES: Multilingual Detection of Offensive SpansSystem Demonstrations44 citations
197. Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModelsLong44 citations
198. Seq2Emo: A Sequence to Multi-Label Emotion Classification ModelLong44 citations
199. Towards Continual Learning for Multilingual Machine Translation via Vocabulary SubstitutionLong44 citations
200. ConVEx: Data-Efficient and Few-Shot Slot LabelingLong43 citations
201. RefSum: Refactoring Neural SummarizationLong43 citations
202. Constructing Taxonomies from Pretrained Language ModelsLong42 citations
203. Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language ModelsLong42 citations
204. On learning and representing social meaning in NLP: a sociolinguistic perspectiveLong42 citations
205. Probing Contextual Language Models for Common Ground with Visual RepresentationsLong42 citations
206. Better Feature Integration for Named Entity RecognitionLong41 citations
207. Faithfully Explainable Recommendation via Neural Logic ReasoningLong41 citations
208. Incorporating External Knowledge to Enhance Tabular ReasoningLong41 citations
209. Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic ResourcesLong41 citations
210. DATE: Detecting Anomalies in Text via Self-Supervision of TransformersLong40 citations
211. Everything Has a Cause: Leveraging Causal Inference in Legal Text AnalysisLong40 citations
212. Improving Evidence Retrieval for Automated Explainable Fact-CheckingSystem Demonstrations40 citations
213. Inductive Topic Variational Graph Auto-Encoder for Text ClassificationLong40 citations
214. MIMOQA: Multimodal Input Multimodal Output Question AnsweringLong40 citations
215. Too Much in Common: Shifting of Embeddings in Transformer Language Models and its ImplicationsLong40 citations
216. An Empirical Comparison of Instance Attribution Methods for NLPLong39 citations
217. COVID-19 Named Entity Recognition for VietnameseLong39 citations
218. Choose Your Own Adventure: Paired Suggestions in Collaborative Writing for Evaluating Story Generation ModelsLong39 citations
219. Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky ProbingLong39 citations
220. Template Filling with Generative TransformersLong39 citations
221. UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra CostLong39 citations
222. APo-VAE: Text Generation in Hyperbolic SpaceLong38 citations
223. Harnessing Multilinguality in Unsupervised Machine Translation for Rare LanguagesLong38 citations
224. Learning to Decompose and Organize Complex TasksLong38 citations
225. Open Hierarchical Relation ExtractionLong38 citations
226. PhoNLP: A joint multi-task learning model for Vietnamese part-of-speech tagging, named entity recognition and dependency parsingSystem Demonstrations38 citations
227. Quality Estimation for Image Captions Based on Large-scale Human EvaluationsLong38 citations
228. SentSim: Crosslingual Semantic Evaluation of Machine TranslationLong38 citations
229. Cross-lingual Cross-modal Pretraining for Multimodal RetrievalLong37 citations
230. DA-Transformer: Distance-aware TransformerLong37 citations
231. Domain Adaptation for Arabic Cross-Domain and Cross-Dialect Sentiment Analysis from Contextualized Word EmbeddingLong37 citations
232. EventPlus: A Temporal Event Understanding PipelineSystem Demonstrations37 citations
233. MetaXL: Meta Representation Transformation for Low-resource Cross-lingual LearningLong37 citations
234. On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic DependenciesLong37 citations
235. Unsupervised Vision-and-Language Pre-training Without Parallel Images and CaptionsLong37 citations
236. “I’m Not Mad”: Commonsense Implications of Negation and ContradictionLong37 citations
237. Code-Mixing on Sesame Street: Dawn of the Adversarial PolyglotsLong36 citations
238. MM-AVS: A Full-Scale Dataset for Multi-modal SummarizationLong36 citations
239. Modular Networks for Compositional Instruction FollowingLong36 citations
240. OodGAN: Generative Adversarial Network for Out-of-Domain Data GenerationIndustry36 citations
241. Should we find another model?: Improving Neural Machine Translation Performance with ONE-Piece Tokenization Method without Model ModificationIndustry36 citations
242. Towards Sentiment and Emotion aided Multi-modal Speech Act Classification in TwitterLong36 citations
243. Counterfactual Supporting Facts Extraction for Explainable Medical Record Based Diagnosis with Graph NetworkLong35 citations
244. Target-Aware Data Augmentation for Stance DetectionLong35 citations
245. Video-aided Unsupervised Grammar InductionLong35 citations
246. Ab Antiquo: Neural Proto-language ReconstructionLong34 citations
247. Hierarchical Transformer for Task Oriented Dialog SystemsLong34 citations
248. Jointly Extracting Explicit and Implicit Relational Triples with Reasoning Pattern Enhanced Binary Pointer NetworkLong34 citations
249. Macro-Average: Rare Types Are Important TooLong34 citations
250. Posterior Differential Regularization with f-divergence for Improving Model RobustnessLong34 citations
251. Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence TasksLong34 citations
252. Self-Supervised Contrastive Learning for Efficient User Satisfaction Prediction in Conversational AgentsLong34 citations
253. Self-Supervised Test-Time Learning for Reading ComprehensionLong34 citations
254. Text Editing by CommandLong34 citations
255. A Non-Linear Structural ProbeLong33 citations
256. Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQALong33 citations
257. Edge: Enriching Knowledge Graph Embeddings with External TextLong33 citations
258. FLIN: A Flexible Natural Language Interface for Web NavigationLong33 citations
259. Non-Autoregressive Translation by Learning Target Categorical CodesLong33 citations
260. TuringAdvice: A Generative and Dynamic Evaluation of Language UseLong33 citations
261. A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference ResolutionLong32 citations
262. Adversarial Self-Supervised Learning for Out-of-Domain DetectionLong32 citations
263. DirectProbe: Studying Representations without ClassifiersLong32 citations
264. Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine TranslationLong32 citations
265. Practical Transformer-based Multilingual Text ClassificationIndustry32 citations
266. CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over ImagesLong31 citations
267. DReCa: A General Task Augmentation Strategy for Few-Shot Natural Language InferenceLong31 citations
268. RST Parsing from ScratchLong31 citations
269. WEC: Deriving a Large-scale Cross-document Event Coreference dataset from WikipediaLong31 citations
270. Augmenting Knowledge-grounded Conversations with Sequential Knowledge TransitionLong30 citations
271. Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language ModelsLong30 citations
272. Multi-Step Reasoning Over Unstructured Text with Beam Dense RetrievalLong30 citations
273. Case Study: Deontological Ethics in NLPLong29 citations
274. DuoRAT: Towards Simpler Text-to-SQL ModelsLong29 citations
275. Dynamically Disentangling Social Bias from Task-Oriented Representations with Adversarial AttackLong29 citations
276. Modeling the Severity of Complaints in Social MediaLong29 citations
277. Training Data Augmentation for Code-Mixed TranslationLong29 citations
278. multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule ReasoningLong29 citations
279. Extracting a Knowledge Base of Mechanisms from COVID-19 PapersLong28 citations
280. Pruning-then-Expanding Model for Domain Adaptation of Neural Machine TranslationLong28 citations
281. RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph CompletionLong28 citations
282. Reading and Acting while Blindfolded: The Need for Semantics in Text Game AgentsLong28 citations
283. SGL: Speaking the Graph Languages of Semantic Parsing via Multilingual TranslationLong28 citations
284. Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base PriorsLong27 citations
285. Identifying Helpful Sentences in Product ReviewsLong27 citations
286. On Unifying Misinformation DetectionLong27 citations
287. Time-Stamped Language Model: Teaching Language Models to Understand The Flow of EventsLong27 citations
288. Translational NLP: A New Paradigm and General Principles for Natural Language Processing ResearchLong27 citations
289. Context Tracking Network: Graph-based Context Modeling for Implicit Discourse Relation RecognitionLong26 citations
290. Discrete Argument Representation Learning for Interactive Argument Pair IdentificationLong26 citations
291. Extending Multi-Document Summarization Evaluation to the Interactive SettingLong26 citations
292. Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes AnalysisLong26 citations
293. Lifelong Learning of Hate Speech Classification on Social MediaLong26 citations
294. Masked Conditional Random Fields for Sequence LabelingLong26 citations
295. Non-Autoregressive Semantic Parsing for Compositional Task-Oriented DialogLong26 citations
296. Quantitative Day Trading from Natural Language using Reinforcement LearningLong26 citations
297. Breadth First Reasoning Graph for Multi-hop Question AnsweringLong25 citations
298. Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group MasksLong25 citations
299. Game-theoretic Vocabulary Selection via the Shapley Value and Banzhaf IndexLong25 citations
300. Identifying Medical Self-Disclosure in Online CommunitiesLong25 citations
301. Incorporating Syntax and Semantics in Coreference Resolution with Heterogeneous Graph Attention NetworkLong25 citations
302. Revisiting Simple Neural Probabilistic Language ModelsLong25 citations
303. Graph-based Multilingual Product Retrieval in E-Commerce SearchIndustry24 citations
304. Identifying inherent disagreement in natural language inferenceLong24 citations
305. Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy ReasoningLong24 citations
306. Knowledge Guided Metric Learning for Few-Shot Text ClassificationLong24 citations
307. Latent-Optimized Adversarial Neural Transfer for Sarcasm DetectionLong24 citations
308. Neural Quality Estimation with Multiple Hypotheses for Grammatical Error CorrectionLong24 citations
309. Profiling of Intertextuality in Latin Literature Using Word EmbeddingsLong24 citations
310. A Disentangled Adversarial Neural Topic Model for Separating Opinions from Plots in User ReviewsLong23 citations
311. A Unified Span-Based Approach for Opinion Mining with Syntactic ConstituentsLong23 citations
312. CREAD: Combined Resolution of Ellipses and Anaphora in DialoguesLong23 citations
313. Continual Learning for Neural Machine TranslationLong23 citations
314. Heterogeneous Graph Neural Networks for Concept Prerequisite Relation Learning in Educational DataLong23 citations
315. PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many SymbolsLong23 citations
316. Pre-training with Meta Learning for Chinese Word SegmentationLong23 citations
317. X-METRA-ADA: Cross-lingual Meta-Transfer learning Adaptation to Natural Language Understanding and Question AnsweringLong23 citations
318. Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue SystemsSystem Demonstrations22 citations
319. An Empirical Investigation of Bias in the Multimodal Analysis of Financial Earnings CallsLong22 citations
320. Assessing Reference-Free Peer Evaluation for Machine TranslationLong22 citations
321. Evaluating the Values of Sources in Transfer LearningLong22 citations
322. How (Non-)Optimal is the Lexicon?Long22 citations
323. Non-Parametric Few-Shot Learning for Word Sense DisambiguationLong22 citations
324. Preregistering NLP researchLong22 citations
325. Probing for Bridging Inference in Transformer Language ModelsLong22 citations
326. Swords: A Benchmark for Lexical Substitution with Improved Data Coverage and QualityLong22 citations
327. BBAEG: Towards BERT-based Biomedical Adversarial Example Generation for Text ClassificationLong21 citations
328. Constrained Multi-Task Learning for Event Coreference ResolutionLong21 citations
329. Enriching Transformers with Structured Tensor-Product Representations for Abstractive SummarizationLong21 citations
330. Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine TranslationLong21 citations
331. Multi-Style Transfer with Discriminative Feedback on Disjoint CorpusLong21 citations
332. OCID-Ref: A 3D Robotic Dataset With Embodied Language For Clutter Scene GroundingLong21 citations
333. Target-specified Sequence Labeling with Multi-head Self-attention for Target-oriented Opinion Words ExtractionLong21 citations
334. An Emotional Comfort Framework for Improving User Satisfaction in E-Commerce Customer Service ChatbotsIndustry20 citations
335. Answering Product-Questions by Utilizing Questions from Other Contextually Similar ProductsLong20 citations
336. Explainable Multi-hop Verbal Reasoning Through Internal MonologueLong20 citations
337. GPT Perdetry Test: Generating new meanings for new wordsLong20 citations
338. How Robust are Fact Checking Systems on Colloquial Claims?Long20 citations
339. Is Incoherence Surprising? Targeted Evaluation of Coherence Prediction from Language ModelsLong20 citations
340. Proteno: Text Normalization with Limited Data for Fast Deployment in Text to Speech SystemsIndustry20 citations
341. Query2Prod2Vec: Grounded Word Embeddings for eCommerceIndustry20 citations
342. Redefining Absent Keyphrases and their Effect on Retrieval EffectivenessLong20 citations
343. Smoothing and Shrinking the Sparse Seq2Seq Search SpaceLong20 citations
344. A Deep Metric Learning Approach to Account LinkingLong19 citations
345. A Simple and Efficient Multi-Task Learning Approach for Conditioned Dialogue GenerationLong19 citations
346. Ad Headline Generation using Self-Critical Masked Language ModelIndustry19 citations
347. An Empirical Study of Generating Texts for Search Engine AdvertisingIndustry19 citations
348. Did they answer? Subjective acts and intents in conversational discourseLong19 citations
349. Inference Time Style Control for SummarizationLong19 citations
350. Neural Language Modeling for Contextualized Temporal Graph GenerationLong19 citations
351. Neural Machine Translation without EmbeddingsLong19 citations
352. Static Embeddings as Efficient Knowledge Bases?Long19 citations
353. Video Question Answering with Phrases via Semantic RolesLong19 citations
354. Word Complexity is in the Eye of the BeholderLong19 citations
355. tWT–WT: A Dataset to Assert the Role of Target Entities for Detecting Stance of TweetsLong19 citations
356. Capturing Row and Column Semantics in Transformer Based Question Answering over TablesLong18 citations
357. Fast and Scalable Dialogue State Tracking with Explicit Modular DecompositionLong18 citations
358. MUSER: MUltimodal Stress detection using Emotion Recognition as an Auxiliary TaskLong18 citations
359. Restoring and Mining the Records of the Joseon Dynasty via Neural Language Modeling and Machine TranslationLong18 citations
360. Event Time Extraction and Propagation via Graph Attention NetworksLong17 citations
361. Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic ModelingLong17 citations
362. Improving Neural RST Parsing Model with Silver Agreement SubtreesLong17 citations
363. Modeling Event Plausibility with Consistent Conceptual AbstractionLong17 citations
364. Multi-Grained Knowledge Distillation for Named Entity RecognitionLong17 citations
365. News Headline Grouping as a Challenging NLU TaskLong17 citations
366. On the Impact of Random Seeds on the Fairness of Clinical ClassifiersLong17 citations
367. Plot-guided Adversarial Example Construction for Evaluating Open-domain Story GenerationLong17 citations
368. A recipe for annotating grounded clarificationsLong16 citations
369. ENTRUST: Argument Reframing with Language Models and EntailmentLong16 citations
370. From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language UnderstandingLong16 citations
371. Human-like informative conversations: Better acknowledgements using conditional mutual informationLong16 citations
372. Linking Entities to Unseen Knowledge Bases with Arbitrary SchemasLong16 citations
373. Robust Question Answering Through Sub-part AlignmentLong16 citations
374. Spoken Language Understanding for Task-oriented Dialogue Systems with Augmented Memory NetworksLong16 citations
375. Towards Modeling the Style of Translators in Neural Machine TranslationLong16 citations
376. A New Approach to Overgenerating and Scoring Abstractive SummariesLong15 citations
377. Active2 Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine TranslationLong15 citations
378. Attention Head Masking for Inference Time Content Selection in Abstractive SummarizationLong15 citations
379. Benchmarking Commercial Intent Detection Services with Practice-Driven EvaluationsIndustry15 citations
380. Context-aware Decoder for Neural Machine Translation using a Target-side Document-Level Language ModelLong15 citations
381. Diversity-Aware Batch Active Learning for Dependency ParsingLong15 citations
382. Modeling Diagnostic Label Correlation for Automatic ICD CodingLong15 citations
383. MultiOpEd: A Corpus of Multi-Perspective News EditorialsLong15 citations
384. Multitasking Inhibits Semantic DriftLong15 citations
385. Predicting Discourse Trees from Transformer-based Neural SummarizersLong15 citations
386. RECONSIDER: Improved Re-Ranking using Span-Focused Cross-Attention for Open Domain Question AnsweringLong15 citations
387. ReadTwice: Reading Very Large Documents with MemoriesLong15 citations
388. SGG: Learning to Select, Guide, and Generate for Keyphrase GenerationLong15 citations
389. Stay Together: A System for Single and Split-antecedent Anaphora ResolutionLong15 citations
390. The structure of online social networks modulates the rate of lexical changeLong15 citations
391. Wikipedia Entities as Rendezvous across Languages: Grounding Multilingual Language Models by Predicting Wikipedia HyperlinksLong15 citations
392. ActiveAnno: General-Purpose Document-Level Annotation Tool with Active Learning IntegrationSystem Demonstrations14 citations
393. Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World KnowledgeLong14 citations
394. Bridging Resolution: Making Sense of the State of the ArtLong14 citations
395. Cross-Lingual Word Embedding Refinement by ℓ1 Norm OptimisationLong14 citations
396. DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response GenerationSystem Demonstrations14 citations
397. Event Representation with Sequential, Semi-Supervised Discrete VariablesLong14 citations
398. Multi-Adversarial Learning for Cross-Lingual Word EmbeddingsLong14 citations
399. Multi-Hop Transformer for Document-Level Machine TranslationLong14 citations
400. Text Generation from Discourse Representation StructuresLong14 citations
401. When and Why a Model Fails? A Human-in-the-loop Error Detection Framework for Sentiment AnalysisIndustry14 citations
402. Autocorrect in the Process of Translation — Multi-task Learning Improves Dialogue Machine TranslationIndustry13 citations
403. Contextualized and Generalized Sentence Representations by Contrastive Self-Supervised Learning: A Case Study on Discourse Relation AnalysisLong13 citations
404. Discovering Better Model Architectures for Medical Query UnderstandingIndustry13 citations
405. End-to-end ASR to jointly predict transcriptions and linguistic annotationsLong13 citations
406. If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question AnsweringLong13 citations
407. KPQA: A Metric for Generative Question Answering Using Keyphrase WeightsLong13 citations
408. LATEX-Numeric: Language Agnostic Text Attribute Extraction for Numeric AttributesIndustry13 citations
409. Neural Network Surgery: Injecting Data Patterns into Pre-trained Models with Minimal Instance-wise Side EffectsLong13 citations
410. Probing Word Translations in the Transformer and Trading Decoder for Encoder LayersLong13 citations
411. A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source CodeLong12 citations
412. AVA: an Automatic eValuation Approach for Question Answering SystemsLong12 citations
413. Double Perturbation: On the Robustness of Robustness and Counterfactual Bias EvaluationLong12 citations
414. FITAnnotator: A Flexible and Intelligent Text Annotation SystemSystem Demonstrations12 citations
415. Generating Negative Samples by Manipulating Golden Responses for Unsupervised Learning of a Response Evaluation ModelLong12 citations
416. Machine Translated Text Detection Through Text Similarity with Round-Trip TranslationLong12 citations
417. Mediators in Determining what Processing BERT Performs FirstLong12 citations
418. On the Use of Context for Predicting Citation Worthiness of Sentences in Scholarly ArticlesLong12 citations
419. Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data ScenariosLong12 citations
420. When does text prediction benefit from additional context? An exploration of contextual signals for chat and email messagesIndustry12 citations
421. A Comparative Study on Schema-Guided Dialogue State TrackingLong11 citations
422. Automatic Classification of Neutralization Techniques in the Narrative of Climate Change ScepticismLong11 citations
423. CoRT: Complementary Rankings from TransformersLong11 citations
424. Decompose, Fuse and Generate: A Formation-Informed Method for Chinese Definition GenerationLong11 citations
425. Designing a Minimal Retrieve-and-Read System for Open-Domain Question AnsweringLong11 citations
426. Entity Resolution in Open-domain ConversationsIndustry11 citations
427. Framing Unpacked: A Semi-Supervised Interpretable Multi-View Model of Media FramesLong11 citations
428. Learning from Executions for Semantic ParsingLong11 citations
429. Variance-reduced First-order Meta-learning for Natural Language Processing TasksLong11 citations
430. Adapting Coreference Resolution for Processing Violent Death NarrativesLong10 citations
431. Learning Syntax from Naturally-Occurring BracketingsLong10 citations
432. Multi-source Neural Topic Modeling in Multi-view Embedding SpacesLong10 citations
433. Nutri-bullets Hybrid: Consensual Multi-document SummarizationLong10 citations
434. QuadrupletBERT: An Efficient Model For Embedding-Based Large-Scale RetrievalLong10 citations
435. Targeted Adversarial Training for Natural Language UnderstandingLong10 citations
436. Technical Question Answering across Tasks and DomainsIndustry10 citations
437. What About the Precedent: An Information-Theoretic Analysis of Common LawLong10 citations
438. Worldly Wise (WoW) - Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question AnsweringLong10 citations
439. Ensemble of MRR and NDCG models for Visual DialogLong9 citations
440. Evaluating the Impact of a Hierarchical Discourse Representation on Entity Coreference Resolution PerformanceLong9 citations
441. Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic OracleLong9 citations
442. Learning to Organize a Bag of Words into Sentences with Neural Networks: An Empirical StudyLong9 citations
443. Linguistic Complexity Loss in Text-Based TherapyLong9 citations
444. Multi-task Learning of Negation and Speculation for Targeted Sentiment ClassificationLong9 citations
445. Multitask Learning for Emotionally Analyzing Sexual Abuse DisclosuresLong9 citations
446. Scalar Adjective Identification and Multilingual RankingLong9 citations
447. Supervised Neural Clustering via Latent Structured Output Learning: Application to Question IntentsLong9 citations
448. Does Structure Matter? Encoding Documents for Machine Reading ComprehensionLong8 citations
449. Finding Concept-specific Biases in Form–Meaning AssociationsLong8 citations
450. FlowPrior: Learning Expressive Priors for Latent Variable Sentence ModelsLong8 citations
451. Knowledge Router: Learning Disentangled Representations for Knowledge GraphsLong8 citations
452. Language in a (Search) Box: Grounding Language Learning in Real-World Human-Machine InteractionLong8 citations
453. Learning to Learn to be Right for the Right ReasonsLong8 citations
454. Leveraging Deep Representations of Radiology Reports in Survival Analysis for Predicting Heart Failure Patient MortalityLong8 citations
455. Machine-Assisted Script CurationSystem Demonstrations8 citations
456. Measuring the ‘I don’t know’ Problem through the Lens of Gricean QuantityLong8 citations
457. On Biasing Transformer Attention Towards MonotonicityLong8 citations
458. Revisiting Document Representations for Large-Scale Zero-Shot LearningLong8 citations
459. SOCCER: An Information-Sparse Discourse State Tracking Collection in the Sports Commentary DomainLong8 citations
460. Supertagging-based Parsing with Linear Context-free Rewriting SystemsLong8 citations
461. Why Do Document-Level Polarity Classifiers Fail?Long8 citations
462. Can Latent Alignments Improve Autoregressive Machine Translation?Long7 citations
463. Cultural and Geographical Influences on Image Translatability of Words across LanguagesLong7 citations
464. Generating An Optimal Interview Question Plan Using A Knowledge Graph And Integer Linear ProgrammingLong7 citations
465. Goodwill Hunting: Analyzing and Repurposing Off-the-Shelf Named Entity Linking SystemsIndustry7 citations
466. Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog ManagementLong7 citations
467. NAMER: A Node-Based Multitasking Framework for Multi-Hop Knowledge Base Question AnsweringSystem Demonstrations7 citations
468. Put Chatbot into Its Interlocutor’s Shoes: New Framework to Learn Chatbot Responding with IntentionLong7 citations
469. SCRIPT: Self-Critic PreTraining of TransformersLong7 citations
470. Semantic Frame ForecastLong7 citations
471. WikiTalkEdit: A Dataset for modeling Editors’ behaviors on WikipediaLong7 citations
472. Cross-lingual Supervision Improves Unsupervised Neural Machine TranslationIndustry6 citations
473. Data Filtering using Cross-Lingual Word EmbeddingsLong6 citations
474. Data and Model Distillation as a Solution for Domain-transferable Fact VerificationLong6 citations
475. Distantly Supervised Transformers For E-Commerce Product QALong6 citations
476. Do RNN States Encode Abstract Phonological Alternations?Long6 citations
477. Larger-Context Tagging: When and Why Does It Work?Long6 citations
478. Negative language transfer in learner English: A new datasetLong6 citations
479. On the Embeddings of Variables in Recurrent Neural Networks for Source CodeLong6 citations
480. Unsupervised Concept Representation Learning for Length-Varying Text SimilarityLong6 citations
481. User-Generated Text Corpus for Evaluating Japanese Morphological Analysis and Lexical NormalizationLong6 citations
482. A Hybrid Approach to Scalable and Robust Spoken Language Understanding in Enterprise Virtual AgentsIndustry5 citations
483. Almost Free Semantic Draft for Neural Machine TranslationLong5 citations
484. EaSe: A Diagnostic Tool for VQA based on Answer DiversityLong5 citations
485. Generalization in Instruction Following SystemsLong5 citations
486. How low is too low? A monolingual take on lemmatisation in Indian languagesLong5 citations
487. Hyperparameter-free Continuous Learning for Domain Classification in Natural Language UnderstandingLong5 citations
488. Integrating Lexical Information into Entity Neighbourhood Representations for Relation PredictionLong5 citations
489. Knowledge-Driven Slot Constraints for Goal-Oriented Dialogue SystemsLong5 citations
490. Multifaceted Domain-Specific Document EmbeddingsSystem Demonstrations5 citations
491. Neural Sequence Segmentation as Determining the Leftmost SegmentsLong5 citations
492. Noise Robust Named Entity Understanding for Voice AssistantsIndustry5 citations
493. Smart-Start Decoding for Neural Machine TranslationLong5 citations
494. SpanPredict: Extraction of Predictive Document Spans with Neural AttentionLong5 citations
495. A Million Tweets Are Worth a Few Points: Tuning Transformers for Customer Service TasksLong4 citations
496. Backtranslation Feedback Improves User Confidence in MT, Not QualityLong4 citations
497. Challenging distributional models with a conceptual network of philosophical termsLong4 citations
498. Continuous Model Improvement for Language Understanding with Machine TranslationIndustry4 citations
499. Cost-effective Deployment of BERT Models in Serverless EnvironmentIndustry4 citations
500. Development of an Enterprise-Grade Contract Understanding SystemIndustry4 citations
501. ReinforceBug: A Framework to Generate Adversarial Textual ExamplesLong4 citations
502. SOrT-ing VQA Models : Contrastive Gradient Learning for Improved ConsistencyLong4 citations
503. Supporting Spanish Writers using Automated FeedbackSystem Demonstrations4 citations
504. TextEssence: A Tool for Interactive Analysis of Semantic Shifts Between CorporaSystem Demonstrations4 citations
505. You Sound Like Someone Who Watches Drama Movies: Towards Predicting Movie Preferences from Conversational InteractionsLong4 citations
506. An Architecture for Accelerated Large-Scale Inference of Transformer-Based Language ModelsIndustry3 citations
507. Identifying and Resolving Annotation Changes for Natural Language UnderstandingIndustry3 citations
508. Label-Guided Learning for Item Categorization in e-CommerceIndustry3 citations
509. Modeling Human Mental States with an Entity-based Narrative GraphLong3 citations
510. Pretrain-Finetune Based Training of Task-Oriented Dialogue Systems in a Real-World SettingIndustry3 citations
511. TITA: A Two-stage Interaction and Topic-Aware Text Matching ModelLong3 citations
512. Bootstrapping a Music Voice Assistant with Weak SupervisionIndustry2 citations
513. Clipping Loops for Sample-Efficient Dialogue Policy OptimisationLong2 citations
514. Coherent and Concise Radiology Report Generation via Context Specific Image Representations and Orthogonal Sentence StatesIndustry2 citations
515. Context-Interactive Pre-Training for Document Machine TranslationLong2 citations
516. Field Embedding: A Unified Grain-Based Framework for Word RepresentationLong2 citations
517. Interactive Plot Manipulation using Natural LanguageSystem Demonstrations2 citations
518. Language Scaling for Universal Suggested Replies ModelIndustry2 citations
519. Learning Paralinguistic Features from Audiobooks through Style Voice ConversionLong2 citations
520. On the Transferability of Minimal Prediction Preserving Inputs in Question AnsweringLong2 citations
521. Optimizing NLU Reranking Using Entity Resolution Signals in Multi-domain Dialog SystemsIndustry2 citations
522. Self Promotion in US Congressional TweetsLong2 citations
523. Semi-Supervised Policy Initialization for Playing Games with Language HintsLong2 citations
524. Universal Semantic Tagging for English and Mandarin ChineseLong2 citations
525. Addressing the Vulnerability of NMT in Input PerturbationsIndustry1 citations
526. Combining Weakly Supervised ML Techniques for Low-Resource NLUIndustry1 citations
527. Contextual Domain Classification with Temporal RepresentationsIndustry1 citations
528. Grouping Words with Semantic DiversityLong1 citations
529. Training Language Models under Resource Constraints for Adversarial Advertisement DetectionIndustry1 citations
530. EnSidNet: Enhanced Hybrid Siamese-Deep Network for grouping clinical trials into drug-development pathwaysLong
531. Exploring the Relationship Between Algorithm Performance, Vocabulary, and Run-Time in Text ClassificationLong
532. Intent Features for Rich Natural Language UnderstandingIndustry
533. Outside Computation with Superior FunctionsLong

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