EMNLP 2022 Accepted Papers

The full list of 1,439 papers accepted at EMNLP 2022 (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.

1001. Unsupervised Entity Linking with Guided Summarization and Multiple-Choice SelectionMain7 citations
1002. Unsupervised Opinion Summarisation in the Wasserstein SpaceMain7 citations
1003. WSpeller: Robust Word Segmentation for Enhancing Chinese Spelling Checkfinding7 citations
1004. What do Large Language Models Learn beyond Language?finding7 citations
1005. Wish I Can Feel What You Feel: A Neural Approach for Empathetic Response Generationfinding7 citations
1006. XLM-D: Decorate Cross-lingual Pre-training Model as Non-Autoregressive Neural Machine TranslationMain7 citations
1007. A Framework for Automatic Generation of Spoken Question-Answering Datafinding6 citations
1008. A Simple Contrastive Learning Framework for Interactive Argument Pair Identification via Argument-Context ExtractionMain6 citations
1009. AX-MABSA: A Framework for Extremely Weakly Supervised Multi-label Aspect Based Sentiment AnalysisMain6 citations
1010. Algorithms for Weighted Pushdown AutomataMain6 citations
1011. CEM: Machine-Human Chatting Handoff via Causal-Enhance ModuleMain6 citations
1012. CLLE: A Benchmark for Continual Language Learning Evaluation in Multilingual Machine Translationfinding6 citations
1013. COMET-QE and Active Learning for Low-Resource Machine Translationfinding6 citations
1014. CORT: A New Baseline for Comparative Opinion Classification by Dual Promptsfinding6 citations
1015. Calibrating Student Models for Emotion-related TasksMain6 citations
1016. Can Visual Context Improve Automatic Speech Recognition for an Embodied Agent?Main6 citations
1017. Commonsense Knowledge Salience Evaluation with a Benchmark Dataset in E-commercefinding6 citations
1018. Contextualizing Language Models for Norms Diverging from Social Majorityfinding6 citations
1019. Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Modelfinding6 citations
1020. Controlled Language Generation for Language Learning ItemsIndustry6 citations
1021. Coordinated Topic ModelingMain6 citations
1022. Curriculum Knowledge Distillation for Emoji-supervised Cross-lingual Sentiment AnalysisMain6 citations
1023. DOROTHIE: Spoken Dialogue for Handling Unexpected Situations in Interactive Autonomous Driving Agentsfinding6 citations
1024. Dialogue Meaning Representation for Task-Oriented Dialogue Systemsfinding6 citations
1025. Do Text-to-Text Multi-Task Learners Suffer from Task Conflict?finding6 citations
1026. Eeny, meeny, miny, moe. How to choose data for morphological inflection.Main6 citations
1027. End-to-End Unsupervised Vision-and-Language Pre-training with Referring Expression MatchingMain6 citations
1028. Explainable Slot Type Attentions to Improve Joint Intent Detection and Slot Fillingfinding6 citations
1029. Explicit Role Interaction Network for Event Argument Extractionfinding6 citations
1030. Exploiting Labeled and Unlabeled Data via Transformer Fine-tuning for Peer-Review Score Predictionfinding6 citations
1031. Exploring the Secrets Behind the Learning Difficulty of Meaning Representations for Semantic ParsingMain6 citations
1032. Federated Model Decomposition with Private Vocabulary for Text ClassificationMain6 citations
1033. Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learningfinding6 citations
1034. GHAN: Graph-Based Hierarchical Aggregation Network for Text-Video RetrievalMain6 citations
1035. Getting the Most out of Simile Recognitionfinding6 citations
1036. Grounded Keys-to-Text Generation: Towards Factual Open-Ended Generationfinding6 citations
1037. Human-in-the-Loop Hate Speech Classification in a Multilingual Contextfinding6 citations
1038. Improved Knowledge Distillation for Pre-trained Language Models via Knowledge Selectionfinding6 citations
1039. Improving Faithfulness by Augmenting Negative Summaries from Fake DocumentsMain6 citations
1040. Incorporating Relevance Feedback for Information-Seeking Retrieval using Few-Shot Document Re-RankingMain6 citations
1041. Infinite SCAN: An Infinite Model of Diachronic Semantic ChangeMain6 citations
1042. Is the Brain Mechanism for Hierarchical Structure Building Universal Across Languages? An fMRI Study of Chinese and EnglishMain6 citations
1043. Learning to Detect Noisy Labels Using Model-Based Featuresfinding6 citations
1044. Leveraging Affirmative Interpretations from Negation Improves Natural Language UnderstandingMain6 citations
1045. LittleBird: Efficient Faster & Longer Transformer for Question AnsweringMain6 citations
1046. Low-resource Neural Machine Translation with Cross-modal AlignmentMain6 citations
1047. MCP: Self-supervised Pre-training for Personalized Chatbots with Multi-level Contrastive Samplingfinding6 citations
1048. MOBA-E2C: Generating MOBA Game Commentaries via Capturing Highlight Events from the Meta-Datafinding6 citations
1049. MOCHA: A Multi-Task Training Approach for Coherent Text Generation from Cognitive PerspectiveMain6 citations
1050. Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language ModelMain6 citations
1051. Near-Negative Distinction: Giving a Second Life to Human Evaluation DatasetsMain6 citations
1052. On Parsing as TaggingMain6 citations
1053. Open World Classification with Adaptive Negative SamplesMain6 citations
1054. Open-Topic False Information Detection on Social Networks with Contrastive Adversarial LearningMain6 citations
1055. PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstandingIndustry6 citations
1056. Pneg: Prompt-based Negative Response Generation for Dialogue Response Selection TaskMain6 citations
1057. R-AT: Regularized Adversarial Training for Natural Language Understandingfinding6 citations
1058. ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural NetworksMain6 citations
1059. Reconciliation of Pre-trained Models and Prototypical Neural Networks in Few-shot Named Entity Recognitionfinding6 citations
1060. Rethinking Multi-Modal Alignment in Multi-Choice VideoQA from Feature and Sample PerspectivesMain6 citations
1061. SEM-F1: an Automatic Way for Semantic Evaluation of Multi-Narrative Overlap Summaries at ScaleMain6 citations
1062. Semantic Framework based Query Generation for Temporal Question Answering over Knowledge GraphsMain6 citations
1063. Semantic Role Labeling Meets Definition Modeling: Using Natural Language to Describe Predicate-Argument Structuresfinding6 citations
1064. SpeechNet: Weakly Supervised, End-to-End Speech Recognition at Industrial ScaleIndustry6 citations
1065. Summarizing Community-based Question-Answer PairsMain6 citations
1066. Syntactically Robust Training on Partially-Observed Data for Open Information Extractionfinding6 citations
1067. T-STAR: Truthful Style Transfer using AMR Graph as Intermediate RepresentationMain6 citations
1068. TINA: Textual Inference with Negation Augmentationfinding6 citations
1069. Text Style Transferring via Adversarial Masking and Styled FillingMain6 citations
1070. Towards Pragmatic Production Strategies for Natural Language Generation TasksMain6 citations
1071. Towards Unifying Reference Expression Generation and ComprehensionMain6 citations
1072. Unsupervised Non-transferable Text ClassificationMain6 citations
1073. Unsupervised Tokenization LearningMain6 citations
1074. Validity Assessment of Legal Will Statements as Natural Language Inferencefinding6 citations
1075. VisToT: Vision-Augmented Table-to-Text GenerationMain6 citations
1076. WordTies: Measuring Word Associations in Language Models via Constrained Samplingfinding6 citations
1077. ACENet: Attention Guided Commonsense Reasoning on Hybrid Knowledge GraphMain5 citations
1078. ADDMU: Detection of Far-Boundary Adversarial Examples with Data and Model Uncertainty EstimationMain5 citations
1079. Adaptive Graph Convolutional Network for Knowledge Graph Entity Alignmentfinding5 citations
1080. Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP ModelsMain5 citations
1081. Biomedical NER for the Enterprise with Distillated BERN2 and the Kazu FrameworkIndustry5 citations
1082. CHIA: CHoosing Instances to Annotate for Machine Translationfinding5 citations
1083. CN-AutoMIC: Distilling Chinese Commonsense Knowledge from Pretrained Language ModelsMain5 citations
1084. Calibrating Zero-shot Cross-lingual (Un-)structured PredictionsMain5 citations
1085. Capturing Topic Framing via Masked Language Modelingfinding5 citations
1086. Collaborative Reasoning on Multi-Modal Semantic Graphs for Video-Grounded Dialogue Generationfinding5 citations
1087. Continuation KD: Improved Knowledge Distillation through the Lens of Continuation Optimizationfinding5 citations
1088. Contrastive Learning enhanced Author-Style Headline GenerationMain5 citations
1089. Correctable-DST: Mitigating Historical Context Mismatch between Training and Inference for Improved Dialogue State TrackingMain5 citations
1090. Cross-Encoder Data Annotation for Bi-Encoder Based Product MatchingIndustry5 citations
1091. Cross-Modal Similarity-Based Curriculum Learning for Image CaptioningMain5 citations
1092. Cross-lingual Text-to-SQL Semantic Parsing with Representation Mixupfinding5 citations
1093. Discrete Cross-Modal Alignment Enables Zero-Shot Speech TranslationMain5 citations
1094. Distinguish Sense from Nonsense: Out-of-Scope Detection for Virtual AssistantsIndustry5 citations
1095. DocFin: Multimodal Financial Prediction and Bias Mitigation using Semi-structured Documentsfinding5 citations
1096. Does Joint Training Really Help Cascaded Speech Translation?Main5 citations
1097. DualNER: A Dual-Teaching framework for Zero-shot Cross-lingual Named Entity Recognitionfinding5 citations
1098. End-to-End Speech to Intent Prediction to improve E-commerce Customer Support Voicebot in Hindi and EnglishIndustry5 citations
1099. Extracting Trigger-sharing Events via an Event Matrixfinding5 citations
1100. Fact Checking Machine Generated Text with Dependency TreesIndustry5 citations
1101. Find Someone Who: Visual Commonsense Understanding in Human-Centric Groundingfinding5 citations
1102. HARALD: Augmenting Hate Speech Data Sets with Real Datafinding5 citations
1103. Helping the Weak Makes You Strong: Simple Multi-Task Learning Improves Non-Autoregressive TranslatorsMain5 citations
1104. IM2: an Interpretable and Multi-category Integrated Metric Framework for Automatic Dialogue EvaluationMain5 citations
1105. Improving English-Arabic Transliteration with Phonemic Memoriesfinding5 citations
1106. JANUS: Joint Autoregressive and Non-autoregressive Training with Auxiliary Loss for Sequence GenerationMain5 citations
1107. Knowledge Distillation Transfer Sets and their Impact on Downstream NLU TasksIndustry5 citations
1108. Knowledge-grounded Dialog State Trackingfinding5 citations
1109. LawngNLI: A Long-Premise Benchmark for In-Domain Generalization from Short to Long Contexts and for Implication-Based Retrievalfinding5 citations
1110. Leveraging Open Data and Task Augmentation to Automated Behavioral Coding of Psychotherapy Conversations in Low-Resource Scenariosfinding5 citations
1111. Lexical Generalization Improves with Larger Models and Longer Trainingfinding5 citations
1112. Logical Neural Networks for Knowledge Base Completion with Embeddings & RulesMain5 citations
1113. Machine translation impact in E-commerce multilingual searchIndustry5 citations
1114. McPhraSy: Multi-Context Phrase Similarity and Clusteringfinding5 citations
1115. Modeling Context With Linear Attention for Scalable Document-Level Translationfinding5 citations
1116. Multimodal Robustness for Neural Machine TranslationMain5 citations
1117. Multiple Instance Learning for Offensive Language Detectionfinding5 citations
1118. Named Entity Recognition in Industrial Tables using Tabular Language ModelsIndustry5 citations
1119. No Word Embedding Model Is Perfect: Evaluating the Representation Accuracy for Social Bias in the Mediafinding5 citations
1120. PLATO-Ad: A Unified Advertisement Text Generation Framework with Multi-Task Prompt LearningIndustry5 citations
1121. Predicting Prerequisite Relations for Unseen ConceptsMain5 citations
1122. QaDialMoE: Question-answering Dialogue based Fact Verification with Mixture of Expertsfinding5 citations
1123. RelU-Net: Syntax-aware Graph U-Net for Relational Triple ExtractionMain5 citations
1124. Rethinking the Authorship Verification Experimental SetupsMain5 citations
1125. Retrofitting Multilingual Sentence Embeddings with Abstract Meaning RepresentationMain5 citations
1126. SMSMix: Sense-Maintained Sentence Mixup for Word Sense Disambiguationfinding5 citations
1127. Semantic Novelty Detection and Characterization in Factual Text Involving Named EntitiesMain5 citations
1128. Semantic Simplification for Sentiment ClassificationMain5 citations
1129. Semi-supervised Adversarial Text Generation based on Seq2Seq modelsIndustry5 citations
1130. Sentence-Incremental Neural Coreference ResolutionMain5 citations
1131. Sequence Models for Document Structure Identification in an Undeciphered ScriptMain5 citations
1132. Structurally Diverse Sampling for Sample-Efficient Training and Comprehensive Evaluationfinding5 citations
1133. StuBot: Learning by Teaching a Conversational Agent Through Machine Reading Comprehensionfinding5 citations
1134. Topic-Regularized Authorship Representation LearningMain5 citations
1135. Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP SystemsMain5 citations
1136. TransAdv: A Translation-based Adversarial Learning Framework for Zero-Resource Cross-Lingual Named Entity Recognitionfinding5 citations
1137. Translating Hanja Historical Documents to Contemporary Korean and Englishfinding5 citations
1138. Tutoring Helps Students Learn Better: Improving Knowledge Distillation for BERT with Tutor NetworkMain5 citations
1139. Understanding Social Media Cross-Modality Discourse in Linguistic Spacefinding5 citations
1140. UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood LearningMain5 citations
1141. Unsupervised Term Extraction for Highly Technical DomainsIndustry5 citations
1142. Word Order Matters When You Increase MaskingMain5 citations
1143. A Comprehensive Comparison of Neural Networks as Cognitive Models of InflectionMain4 citations
1144. A Speaker-Aware Co-Attention Framework for Medical Dialogue Information ExtractionMain4 citations
1145. ALFRED-L: Investigating the Role of Language for Action Learning in Interactive Visual EnvironmentsMain4 citations
1146. Adaptive Token-level Cross-lingual Feature Mixing for Multilingual Neural Machine TranslationMain4 citations
1147. Agent-Specific Deontic Modality Detection in Legal LanguageMain4 citations
1148. Alleviating Sparsity of Open Knowledge Graphs with Ternary Contrastive Learningfinding4 citations
1149. An Empirical Study on Finding SpansMain4 citations
1150. An Unsupervised, Geometric and Syntax-aware Quantification of PolysemyMain4 citations
1151. Audience-Centric Natural Language Generation via Style Infusionfinding4 citations
1152. Borrowing Human Senses: Comment-Aware Self-Training for Social Media Multimodal ClassificationMain4 citations
1153. Can AMR Assist Legal and Logical Reasoning?finding4 citations
1154. Continued Pretraining for Better Zero- and Few-Shot PromptabilityMain4 citations
1155. Cross-domain Generalization for AMR ParsingMain4 citations
1156. Cross-lingual neural fuzzy matching for exploiting target-language monolingual corpora in computer-aided translationMain4 citations
1157. Discourse Comprehension: A Question Answering Framework to Represent Sentence ConnectionsMain4 citations
1158. Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL ParsersMain4 citations
1159. Domain Adaptation of Machine Translation with CrowdworkersIndustry4 citations
1160. Effective Pretraining Objectives for Transformer-based Autoencodersfinding4 citations
1161. Entity Extraction in Low Resource Domains with Selective Pre-training of Large Language ModelsMain4 citations
1162. Extending Phrase Grounding with Pronouns in Visual DialoguesMain4 citations
1163. FPT: Improving Prompt Tuning Efficiency via Progressive Trainingfinding4 citations
1164. FastClass: A Time-Efficient Approach to Weakly-Supervised Text ClassificationMain4 citations
1165. Few-shot initializing of Active Learner via Meta-Learningfinding4 citations
1166. FlowEval: A Consensus-Based Dialogue Evaluation Framework Using Segment Act FlowsMain4 citations
1167. GNN-encoder: Learning a Dual-encoder Architecture via Graph Neural Networks for Dense Passage Retrievalfinding4 citations
1168. Grafting Pre-trained Models for Multimodal Headline GenerationIndustry4 citations
1169. Graph-Induced Transformers for Efficient Multi-Hop Question AnsweringMain4 citations
1170. How to Represent Context Better? An Empirical Study on Context Modeling for Multi-turn Response Selectionfinding4 citations
1171. IELM: An Open Information Extraction Benchmark for Pre-Trained Language ModelsMain4 citations
1172. Identifying Human Strategies for Generating Word-Level Adversarial Examplesfinding4 citations
1173. Improving compositional generalization for multi-step quantitative reasoning in question answeringMain4 citations
1174. Language Model Pre-Training with Sparse Latent TypingMain4 citations
1175. Learning Cooperative Interactions for Multi-Overlap Aspect Sentiment Triplet Extractionfinding4 citations
1176. Learning a Grammar Inducer from Massive Uncurated Instructional VideosMain4 citations
1177. Learning to Adapt to Low-Resource Paraphrase GenerationMain4 citations
1178. Learning to Explain Selectively: A Case Study on Question AnsweringMain4 citations
1179. Learning to Generate Overlap Summaries through Noisy Synthetic DataMain4 citations
1180. Learning to Model Multimodal Semantic Alignment for Story Visualizationfinding4 citations
1181. Long Text Generation with Topic-aware Discrete Latent Variable ModelMain4 citations
1182. M3: A Multi-View Fusion and Multi-Decoding Network for Multi-Document Reading ComprehensionMain4 citations
1183. MetaLogic: Logical Reasoning Explanations with Fine-Grained StructureMain4 citations
1184. Modeling Consistency Preference via Lexical Chains for Document-level Neural Machine TranslationMain4 citations
1185. Momentum Contrastive Pre-training for Question AnsweringMain4 citations
1186. Multi-VQG: Generating Engaging Questions for Multiple ImagesMain4 citations
1187. Multimodal Conversation Modelling for Topic Derailment Detectionfinding4 citations
1188. Neural-Symbolic Inference for Robust Autoregressive Graph Parsing via Compositional Uncertainty QuantificationMain4 citations
1189. On the Effectiveness of Automated Metrics for Text Generation Systemsfinding4 citations
1190. PATS: Sensitivity-aware Noisy Learning for Pretrained Language ModelsMain4 citations
1191. PILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled DistillationIndustry4 citations
1192. ParaTag: A Dataset of Paraphrase Tagging for Fine-Grained Labels, NLG Evaluation, and Data AugmentationMain4 citations
1193. Progressive Sentiment Analysis for Code-Switched Text Datafinding4 citations
1194. QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive AdaptationMain4 citations
1195. Realistic Data Augmentation Framework for Enhancing Tabular Reasoningfinding4 citations
1196. Refinement Matters: Textual Description Needs to be Refined for Zero-shot Learningfinding4 citations
1197. Reorder and then Parse, Fast and Accurate Discontinuous Constituency ParsingMain4 citations
1198. RoChBert: Towards Robust BERT Fine-tuning for Chinesefinding4 citations
1199. Robustifying Sentiment Classification by Maximally Exploiting Few CounterfactualsMain4 citations
1200. SEMGraph: Incorporating Sentiment Knowledge and Eye Movement into Graph Model for Sentiment AnalysisMain4 citations
1201. Specializing Multi-domain NMT via Penalizing Low Mutual InformationMain4 citations
1202. Subword-Delimited Downsampling for Better Character-Level Translationfinding4 citations
1203. Synergy with Translation Artifacts for Training and Inference in Multilingual TasksMain4 citations
1204. Syntactic and Semantic Uniformity for Semantic Parsing and Task-Oriented Dialogue Systemsfinding4 citations
1205. Syntax-guided Localized Self-attention by Constituency Syntactic Distancefinding4 citations
1206. TSGP: Two-Stage Generative Prompting for Unsupervised Commonsense Question Answeringfinding4 citations
1207. The Effects of Corpus Choice and Morphosyntax on Multilingual Space Inductionfinding4 citations
1208. Think Beyond Words: Exploring Context-Relevant Visual Commonsense for Diverse Dialogue Generationfinding4 citations
1209. Topic Taxonomy Expansion via Hierarchy-Aware Topic Phrase Generationfinding4 citations
1210. Towards Efficient Dialogue Pre-training with Transferable and Interpretable Latent StructureMain4 citations
1211. Towards Generalized Open Information Extractionfinding4 citations
1212. Towards Reinterpreting Neural Topic Models via Composite ActivationsMain4 citations
1213. Tweet Based Reach Aware Temporal Attention Network for NFT Valuationfinding4 citations
1214. Twist Decoding: Diverse Generators Guide Each OtherMain4 citations
1215. Using Developer Discussions to Guide Fixing Bugs in Softwarefinding4 citations
1216. Weight Perturbation as Defense against Adversarial Word Substitutionsfinding4 citations
1217. A Comprehensive Evaluation of Biomedical Entity-centric SearchIndustry3 citations
1218. Adapting Multilingual Models for Code-Mixed Translationfinding3 citations
1219. An Empirical Revisiting of Linguistic Knowledge Fusion in Language Understanding TasksMain3 citations
1220. Analyzing the Limits of Self-Supervision in Handling Bias in Languagefinding3 citations
1221. Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddingsfinding3 citations
1222. COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language ModelsMain3 citations
1223. CheckHARD: Checking Hard Labels for Adversarial Text Detection, Prediction Correction, and Perturbed Word Suggestionfinding3 citations
1224. Composing Ci with Reinforced Non-autoregressive Text GenerationMain3 citations
1225. Conformal Predictor for Improving Zero-Shot Text Classification EfficiencyMain3 citations
1226. Contrastive Learning with Expectation-Maximization for Weakly Supervised Phrase GroundingMain3 citations
1227. CycleKQR: Unsupervised Bidirectional Keyword-Question RewritingMain3 citations
1228. Detecting Dementia from Long Neuropsychological Interviewsfinding3 citations
1229. DialogConv: A Lightweight Fully Convolutional Network for Multi-view Response SelectionMain3 citations
1230. DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detectionfinding3 citations
1231. Dictionary-Assisted Supervised Contrastive LearningMain3 citations
1232. Different Tunes Played with Equal Skill: Exploring a Unified Optimization Subspace for Parameter-Efficient Tuningfinding3 citations
1233. DiscoSense: Commonsense Reasoning with Discourse ConnectivesMain3 citations
1234. Discourse Context Predictability Effects in Hindi Word OrderMain3 citations
1235. Dynamic Augmentation Data Selection for Few-shot Text Classificationfinding3 citations
1236. Effective and Efficient Query-aware Snippet Extraction for Web SearchMain3 citations
1237. Empathetic and Emotionally Positive Conversation Systems with an Emotion-specific Query-Response Memoryfinding3 citations
1238. Evaluating Parameter Efficient Learning for GenerationMain3 citations
1239. Explainable Question Answering based on Semantic Graph by Global Differentiable Learning and Dynamic Adaptive ReasoningMain3 citations
1240. Exploring Compositional Image Retrieval with Hybrid Compositional Learning and Heuristic Negative Miningfinding3 citations
1241. Generating Textual Adversaries with Minimal Perturbationfinding3 citations
1242. Goal-oriented Vision-and-Dialog Navigation via Reinforcement Learningfinding3 citations
1243. Hard Gate Knowledge Distillation - Leverage Calibration for Robust and Reliable Language ModelMain3 citations
1244. Improving Scheduled Sampling with Elastic Weight Consolidation for Neural Machine Translationfinding3 citations
1245. Improving Text-to-SQL Semantic Parsing with Fine-grained Query UnderstandingIndustry3 citations
1246. Investigating the Robustness of Natural Language Generation from Logical Forms via Counterfactual SamplesMain3 citations
1247. Is NLP Ready for Standardization?finding3 citations
1248. Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Gamesfinding3 citations
1249. Learning When and What to Quote: A Quotation Recommender System with Mutual Promotion of Recommendation and Generationfinding3 citations
1250. LogicNMR: Probing the Non-monotonic Reasoning Ability of Pre-trained Language Modelsfinding3 citations
1251. McQueen: a Benchmark for Multimodal Conversational Query RewriteMain3 citations
1252. MovieUN: A Dataset for Movie Understanding and Narratingfinding3 citations
1253. Multi-Tenant Optimization For Few-Shot Task-Oriented FAQ RetrievalIndustry3 citations
1254. Multimodal Context CarryoverIndustry3 citations
1255. Navigating Connected Memories with a Task-oriented Dialog SystemMain3 citations
1256. Normalizing Mutual Information for Robust Adaptive Training for TranslationMain3 citations
1257. Not to Overfit or Underfit the Source Domains? An Empirical Study of Domain Generalization in Question AnsweringMain3 citations
1258. On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalizationfinding3 citations
1259. POQue: Asking Participant-specific Outcome Questions for a Deeper Understanding of Complex EventsMain3 citations
1260. Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Trainingfinding3 citations
1261. Precisely the Point: Adversarial Augmentations for Faithful and Informative Text GenerationMain3 citations
1262. Prompt-based Connective Prediction Method for Fine-grained Implicit Discourse Relation Recognitionfinding3 citations
1263. Recursive Neural Networks with Bottlenecks Diagnose (Non-)Compositionalityfinding3 citations
1264. Revisiting the Roles of “Text” in Text Gamesfinding3 citations
1265. Semantic-aware Contrastive Learning for More Accurate Semantic ParsingMain3 citations
1266. Snapshot-Guided Domain Adaptation for ELECTRAfinding3 citations
1267. Subword Segmental Language Modelling for Nguni Languagesfinding3 citations
1268. Text Editing as Imitation Gamefinding3 citations
1269. That’s the Wrong Lung! Evaluating and Improving the Interpretability of Unsupervised Multimodal Encoders for Medical DataMain3 citations
1270. The challenges of temporal alignment on Twitter during crisesfinding3 citations
1271. There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference LearningMain3 citations
1272. Training Dynamics for Curriculum Learning: A Study on Monolingual and Cross-lingual NLUMain3 citations
1273. Visualizing the Obvious: A Concreteness-based Ensemble Model for Noun Property Predictionfinding3 citations
1274. What Has Been Enhanced in my Knowledge-Enhanced Language Model?finding3 citations
1275. When More Data Hurts: A Troubling Quirk in Developing Broad-Coverage Natural Language Understanding SystemsMain3 citations
1276. A Major Obstacle for NLP Research: Let’s Talk about Time Allocation!Main2 citations
1277. AMAL: Meta Knowledge-Driven Few-Shot Adapter LearningMain2 citations
1278. Accelerating the Discovery of Semantic Associations from Medical Literature: Mining Relations Between Diseases and SymptomsIndustry2 citations
1279. Adaptive Ranking-based Sample Selection for Weakly Supervised Class-imbalanced Text Classificationfinding2 citations
1280. An Empirical Study on the Transferability of Transformer Modules in Parameter-efficient Fine-tuningMain2 citations
1281. Answer Quality Aware Aggregation for Extractive QA Crowdsourcingfinding2 citations
1282. BARLE: Background-Aware Representation Learning for Background Shift Out-of-Distribution Detectionfinding2 citations
1283. Break it Down into BTS: Basic, Tiniest Subword Units for KoreanMain2 citations
1284. Bridging the Training-Inference Gap for Dense Phrase Retrievalfinding2 citations
1285. Chapter Ordering in NovelsMain2 citations
1286. Cheater’s Bowl: Human vs. Computer Search Strategies for Open-Domain QAfinding2 citations
1287. Combinatory Grammar Tells Underlying Relevance among Entitiesfinding2 citations
1288. Composition, Attention, or Both?finding2 citations
1289. Con-NAT: Contrastive Non-autoregressive Neural Machine Translationfinding2 citations
1290. Consecutive Question Generation via Dynamic Multitask Learningfinding2 citations
1291. Describing Sets of Images with Textual-PCAfinding2 citations
1292. Digging Errors in NMT: Evaluating and Understanding Model Errors from Partial Hypothesis SpaceMain2 citations
1293. Distilling Multilingual Transformers into CNNs for Scalable Intent ClassificationIndustry2 citations
1294. Early Guessing for Dialect Identificationfinding2 citations
1295. Entity Embedding Completion for Wide-Coverage Entity Disambiguationfinding2 citations
1296. Exploiting In-Domain Bilingual Corpora for Zero-Shot Transfer Learning in NLU of Intra-Sentential Code-Switching Chatbot InteractionsIndustry2 citations
1297. FCGCL: Fine- and Coarse-Granularity Contrastive Learning for Speech Translationfinding2 citations
1298. Foiling Training-Time Attacks on Neural Machine Translation Systemsfinding2 citations
1299. From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Modelsfinding2 citations
1300. Generalization Differences between End-to-End and Neuro-Symbolic Vision-Language Reasoning Systemsfinding2 citations
1301. Guiding Abstractive Dialogue Summarization with Content Planningfinding2 citations
1302. HashFormers: Towards Vocabulary-independent Pre-trained TransformersMain2 citations
1303. How to Do Things without Words: Modeling Semantic Drift of Emojifinding2 citations
1304. How to Stop an Avalanche? JoDeM: Joint Decision Making through Compare and Contrast for Dialog State Trackingfinding2 citations
1305. Identifying Physical Object Use in SentencesMain2 citations
1306. Improving Embeddings Representations for Comparing Higher Education Curricula: A Use Case in ComputingMain2 citations
1307. Improving Few-Shot Domain Transfer for Named Entity Disambiguation with Pattern Exploitationfinding2 citations
1308. Improving Large-Scale Conversational Assistants using Model Interpretation based Training Sample SelectionIndustry2 citations
1309. Improving Precancerous Case Characterization via Transformer-based Ensemble LearningIndustry2 citations
1310. Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiersfinding2 citations
1311. Language Model Detoxification in Dialogue with Contextualized Stance Controlfinding2 citations
1312. Language Models Understand Us, Poorlyfinding2 citations
1313. Learning Action-Effect Dynamics for Hypothetical Vision-Language Reasoning Taskfinding2 citations
1314. Learning From the Source Document: Unsupervised Abstractive Summarizationfinding2 citations
1315. Learning Geolocations for Cold-Start and Hard-to-Resolve Addresses via Deep Metric LearningIndustry2 citations
1316. Learning Label Modular Prompts for Text Classification in the WildMain2 citations
1317. MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal TextsMain2 citations
1318. Measuring Context-Word Biases in Lexical Semantic DatasetsMain2 citations
1319. MiST: a Large-Scale Annotated Resource and Neural Models for Functions of Modal Verbs in English Scientific Textfinding2 citations
1320. Mixed-effects transformers for hierarchical adaptationMain2 citations
1321. Multi-Path Transformer is Better: A Case Study on Neural Machine Translationfinding2 citations
1322. NarraSum: A Large-Scale Dataset for Abstractive Narrative Summarizationfinding2 citations
1323. Norm-based Noisy Corpora Filtering and Refurbishing in Neural Machine TranslationMain2 citations
1324. Offer a Different Perspective: Modeling the Belief Alignment of Arguments in Multi-party DebatesMain2 citations
1325. Open-domain Video Commentary GenerationMain2 citations
1326. PRO-CS : An Instance-Based Prompt Composition Technique for Code-Switched TasksMain2 citations
1327. ParaMac: A General Unsupervised Paraphrase Generation Framework Leveraging Semantic Constraints and Diversifying Mechanismsfinding2 citations
1328. Partially-Random Initialization: A Smoking Gun for Binarization Hypothesis of BERTfinding2 citations
1329. Predicting Long-Term Citations from Short-Term Linguistic Influencefinding2 citations
1330. Probing Cross-modal Semantics Alignment Capability from the Textual Perspectivefinding2 citations
1331. R-TeaFor: Regularized Teacher-Forcing for Abstractive SummarizationMain2 citations
1332. Recovering Gold from Black Sand: Multilingual Dense Passage Retrieval with Hard and False Negative SamplesMain2 citations
1333. SLICER: Sliced Fine-Tuning for Low-Resource Cross-Lingual Transfer for Named Entity RecognitionMain2 citations
1334. STRUDEL: Structured Dialogue Summarization for Dialogue ComprehensionMain2 citations
1335. Segmenting Numerical Substitution CiphersMain2 citations
1336. Self-supervised Rewiring of Pre-trained Speech Encoders:Towards Faster Fine-tuning with Less Labels in Speech Processingfinding2 citations
1337. Semantic Dependency Parsing with Edge GNNsfinding2 citations
1338. Spectral ProbingMain2 citations
1339. Syntactically Rich Discriminative Training: An Effective Method for Open Information ExtractionMain2 citations
1340. Tackling Temporal Questions in Natural Language Interface to DatabasesIndustry2 citations
1341. Towards Compositional Generalization in Code SearchMain2 citations
1342. Towards Inter-character Relationship-driven Story GenerationMain2 citations
1343. Unbiased and Efficient Sampling of Dependency TreesMain2 citations
1344. Understanding ME? Multimodal Evaluation for Fine-grained Visual CommonsenseMain2 citations
1345. Unsupervised Learning of Hierarchical Conversation Structurefinding2 citations
1346. Unsupervised training data re-weighting for natural language understanding with local distribution approximationIndustry2 citations
1347. Weakly Supervised Headline Dependency Parsingfinding2 citations
1348. You Are What You Talk About: Inducing Evaluative Topics for Personality Analysisfinding2 citations
1349. Zero-Shot Dynamic Quantization for Transformer InferenceIndustry2 citations
1350. A Joint Learning Framework for Restaurant Survival Prediction and ExplanationMain1 citations
1351. A Localized Geometric Method to Match Knowledge in Low-dimensional Hyperbolic SpaceMain1 citations
1352. A POMDP Dialogue Policy with 3-way Grounding and Adaptive Sensing for Learning through Communicationfinding1 citations
1353. ARTIST: A Transformer-based Chinese Text-to-Image Synthesizer Digesting Linguistic and World Knowledgefinding1 citations
1354. AdapterShare: Task Correlation Modeling with Adapter DifferentiationMain1 citations
1355. Affective Idiosyncratic Responses to MusicMain1 citations
1356. Algorithms for Acyclic Weighted Finite-State Automata with Failure ArcsMain1 citations
1357. An Anchor-based Relative Position Embedding Method for Cross-Modal TasksMain1 citations
1358. Automatic Scene-based Topic Channel Construction System for E-CommerceIndustry1 citations
1359. Bringing the State-of-the-Art to Customers: A Neural Agent Assistant Framework for Customer Service SupportIndustry1 citations
1360. Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality?Main1 citations
1361. Data Cartography for Low-Resource Neural Machine Translationfinding1 citations
1362. Dealing with Abbreviations in the Slovenian Biographical LexiconMain1 citations
1363. Do Children Texts Hold The Key To Commonsense Knowledge?Main1 citations
1364. DynaMaR: Dynamic Prompt with Mask Token RepresentationIndustry1 citations
1365. Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating AttentionMain1 citations
1366. FormLM: Recommending Creation Ideas for Online Forms by Modelling Semantic and Structural InformationMain1 citations
1367. Guiding Neural Machine Translation with Semantic Kernelsfinding1 citations
1368. HeLo: Learning-Free Lookahead Decoding for Conversation Infillingfinding1 citations
1369. IRRGN: An Implicit Relational Reasoning Graph Network for Multi-turn Response SelectionMain1 citations
1370. Inducing Generalizable and Interpretable Lexicafinding1 citations
1371. Instance Regularization for Discriminative Language Model Pre-trainingMain1 citations
1372. Instance-Guided Prompt Learning for Few-Shot Text Matchingfinding1 citations
1373. Language Model Decomposition: Quantifying the Dependency and Correlation of Language ModelsMain1 citations
1374. Large-scale Machine Translation for Indian Languages in E-commerce under Low Resource ConstraintsIndustry1 citations
1375. Learning Invariant Representation Improves Robustness for MRC Modelsfinding1 citations
1376. Leveraging Only the Category Name for Aspect Detection through Prompt-based Constrained Clusteringfinding1 citations
1377. Lexical Entailment with Hierarchy Representations by Deep Metric Learningfinding1 citations
1378. Lexicon-Enhanced Self-Supervised Training for Multilingual Dense Retrievalfinding1 citations
1379. Machine Translation Robustness to Natural Asemantic VariationMain1 citations
1380. Masked Language Models Know Which are Popular: A Simple Ranking Strategy for Commonsense Question Answeringfinding1 citations
1381. MatRank: Text Re-ranking by Latent Preference Matrixfinding1 citations
1382. Meta-learning Pathologies from Radiology Reports using Variance Aware Prototypical NetworksIndustry1 citations
1383. MetaFill: Text Infilling for Meta-Path Generation on Heterogeneous Information NetworksMain1 citations
1384. Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoderfinding1 citations
1385. NaturalAdversaries: Can Naturalistic Adversaries Be as Effective as Artificial Adversaries?finding1 citations
1386. Opinion Summarization by Weak-Supervision from Mix-structured DataMain1 citations
1387. PAIGE: Personalized Adaptive Interactions Graph Encoder for Query Rewriting in Dialogue SystemsIndustry1 citations
1388. PRINCE: Prefix-Masked Decoding for Knowledge Enhanced Sequence-to-Sequence Pre-TrainingMain1 citations
1389. ProofInfer: Generating Proof via Iterative Hierarchical InferenceMain1 citations
1390. Pseudo-Relevance for Enhancing Document RepresentationMain1 citations
1391. Quality Scoring of Source Words in Neural Translation ModelsMain1 citations
1392. R2F: A General Retrieval, Reading and Fusion Framework for Document-level Natural Language InferenceMain1 citations
1393. Recurrence Boosts Diversity! Revisiting Recurrent Latent Variable in Transformer-Based Variational AutoEncoder for Diverse Text Generationfinding1 citations
1394. RedApt: An Adaptor for wav2vec 2 EncodingFaster and Smaller Speech Translation without Quality Compromisefinding1 citations
1395. Rethinking Style Transformer with Energy-based Interpretation: Adversarial Unsupervised Style Transfer using a Pretrained ModelMain1 citations
1396. Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?Main1 citations
1397. SEEN: Structured Event Enhancement Network for Explainable Need Detection of Information Recall AssistanceMain1 citations
1398. Seeded Hierarchical Clustering for Expert-Crafted Taxonomiesfinding1 citations
1399. Self-training with Two-phase Self-augmentation for Few-shot Dialogue Generationfinding1 citations
1400. Sequential Topic Selection Model with Latent Variable for Topic-Grounded Dialoguefinding1 citations
1401. Status Biases in Deliberation Online: Evidence from a Randomized Experiment on ChangeMyViewfinding1 citations
1402. Structural Constraints and Natural Language Inference for End-to-End Flowchart Grounded Dialog Response GenerationMain1 citations
1403. Summarizing Procedural Text: Data and Approachfinding1 citations
1404. The Curious Case of ControlMain1 citations
1405. Towards Explaining Subjective Ground of Individuals on Social Mediafinding1 citations
1406. Tractable & Coherent Multi-Document Summarization: Discrete Optimization of Multiple Neural Modeling Streams via Integer Linear ProgrammingIndustry1 citations
1407. Unsupervised Dense Retrieval for Scientific ArticlesIndustry1 citations
1408. Unsupervised Domain Adaptation for Joint Information Extractionfinding1 citations
1409. Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignmentfinding1 citations
1410. “Covid vaccine is against Covid but Oxford vaccine is made at Oxford!” Semantic Interpretation of Proper Noun CompoundsMain1 citations
1411. “I Know Who You Are”: Character-Based Features for Conversational Humor Recognition in Chinesefinding1 citations
1412. A Hybrid Approach to Cross-lingual Product Review SummarizationIndustry
1413. A Stacking-based Efficient Method for Toxic Language Detection on Live Streaming ChatIndustry
1414. Assessing Non-autoregressive Alignment in Neural Machine Translation via Word Reorderingfinding
1415. Automatic Rule Induction for Efficient Semi-Supervised Learningfinding
1416. Baked-in State Probingfinding
1417. CoCoID: Learning Contrastive Representations and Compact Clusters for Semi-Supervised Intent DiscoveryIndustry
1418. Dense Feature Memory Augmented Transformers for COVID-19 Vaccination Search ClassificationIndustry
1419. Deploying Unified BERT Moderation Model for E-Commerce ReviewsIndustry
1420. Deploying a Retrieval based Response Model for Task Oriented DialoguesIndustry
1421. Detecting Languages Unintelligible to Multilingual Models through Local Structure Probesfinding
1422. DiffG-RL: Leveraging Difference between Environment State and Common Sensefinding
1423. End-to-End Neural Discourse Deixis Resolution in DialogueMain
1424. Exploration of the Usage of Color Terms by Color-blind Participants in Online Discussion PlatformsMain
1425. Explore Unsupervised Structures in Pretrained Models for Relation Extractionfinding
1426. Exploring Logographic Image for Chinese Aspect-based Sentiment Classificationfinding
1427. GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved GeneralizationMain
1428. Impact of Pretraining Term Frequencies on Few-Shot Numerical Reasoningfinding
1429. Improving the Extraction of Supertags for Constituency Parsing with Linear Context-Free Rewriting Systemsfinding
1430. Is it out yet? Automatic Future Product Releases Extraction from Web DataIndustry
1431. Iterative Stratified Testing and Measurement for Automated Model UpdatesIndustry
1432. Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddingsfinding
1433. On Utilizing Constituent Language Resources to Improve Downstream Tasks in Hinglishfinding
1434. On the Curious Case of l2 norm of Sense Embeddingsfinding
1435. P3LM: Probabilistically Permuted Prophet Language Modeling for Generative Pre-Trainingfinding
1436. Parameter-free Automatically Prompting: A Latent Pseudo Label Mapping Model for Prompt-based Learningfinding
1437. SLATE: A Sequence Labeling Approach for Task Extraction from Free-form Inked ContentIndustry
1438. Third-Party Aligner for Neural Word Alignmentsfinding
1439. Towards Need-Based Spoken Language Understanding Model Updates: What Have We Learned?Industry

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