ACL 2023 Accepted Papers

The full list of 2,052 papers accepted at ACL 2023 (Association for Computational Linguistics). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

1001. Computer says “No”: The Case Against Empathetic Conversational AIFindings10 citations
1002. Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop PathsLong10 citations
1003. Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation ExtractionLong10 citations
1004. Distill or Annotate? Cost-Efficient Fine-Tuning of Compact ModelsLong10 citations
1005. Distilling Calibrated Knowledge for Stance DetectionFindings10 citations
1006. Distractor Generation based on Text2Text Language Models with Pseudo Kullback-Leibler Divergence RegulationFindings10 citations
1007. Don’t Retrain, Just Rewrite: Countering Adversarial Perturbations by Rewriting TextLong10 citations
1008. Dual Class Knowledge Propagation Network for Multi-label Few-shot Intent DetectionLong10 citations
1009. Dynamic Structured Neural Topic Model with Self-Attention MechanismFindings10 citations
1010. Dynamic Transformers Provide a False Sense of EfficiencyLong10 citations
1011. Easy-to-Hard Learning for Information ExtractionFindings10 citations
1012. Enhancing Cross-lingual Natural Language Inference by Soft Prompting with Multilingual VerbalizerFindings10 citations
1013. Feature Interactions Reveal Linguistic Structure in Language ModelsFindings10 citations
1014. FiD-ICL: A Fusion-in-Decoder Approach for Efficient In-Context LearningLong10 citations
1015. Fighting Bias With Bias: Promoting Model Robustness by Amplifying Dataset BiasesFindings10 citations
1016. Focused Prefix Tuning for Controllable Text GenerationShort10 citations
1017. Generating EDU Extracts for Plan-Guided Summary Re-RankingLong10 citations
1018. Gradient-based Intra-attention Pruning on Pre-trained Language ModelsLong10 citations
1019. HistRED: A Historical Document-Level Relation Extraction DatasetLong10 citations
1020. Holographic CCG ParsingLong10 citations
1021. Honey, I Shrunk the Language: Language Model Behavior at Reduced Scale.Findings10 citations
1022. How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation ObjectivesShort10 citations
1023. Improving Gradient Trade-offs between Tasks in Multi-task Text ClassificationLong10 citations
1024. Investigating Glyph-Phonetic Information for Chinese Spell Checking: What Works and What’s Next?Findings10 citations
1025. Large Scale Generative Multimodal Attribute Extraction for E-commerce AttributesIndustry10 citations
1026. Less Likely Brainstorming: Using Language Models to Generate Alternative HypothesesFindings10 citations
1027. Local Byte Fusion for Neural Machine TranslationLong10 citations
1028. Long-Tailed Question Answering in an Open WorldLong10 citations
1029. MDACE: MIMIC Documents Annotated with Code EvidenceLong10 citations
1030. MeetingQA: Extractive Question-Answering on Meeting TranscriptsLong10 citations
1031. Modeling Adversarial Attack on Pre-trained Language Models as Sequential Decision MakingFindings10 citations
1032. Modeling Appropriate Language in ArgumentationLong10 citations
1033. Multi-Level Knowledge Distillation for Out-of-Distribution Detection in TextLong10 citations
1034. Noisy Positive-Unlabeled Learning with Self-Training for Speculative Knowledge Graph ReasoningFindings10 citations
1035. Numeric Magnitude Comparison Effects in Large Language ModelsFindings10 citations
1036. On Text-based Personality Computing: Challenges and Future DirectionsFindings10 citations
1037. On the Role of Parallel Data in Cross-lingual Transfer LearningFindings10 citations
1038. Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain AdaptationLong10 citations
1039. Prompts Can Play Lottery Tickets Well: Achieving Lifelong Information Extraction via Lottery Prompt TuningLong10 citations
1040. Query Structure Modeling for Inductive Logical Reasoning Over Knowledge GraphsLong10 citations
1041. Reference Matters: Benchmarking Factual Error Correction for Dialogue Summarization with Fine-grained Evaluation FrameworkLong10 citations
1042. SLABERT Talk Pretty One Day: Modeling Second Language Acquisition with BERTLong10 citations
1043. Second Language Acquisition of Neural Language ModelsFindings10 citations
1044. Single Sequence Prediction over Reasoning Graphs for Multi-hop QALong10 citations
1045. Substitution-based Semantic Change Detection using Contextual EmbeddingsShort10 citations
1046. Synthesize, Prompt and Transfer: Zero-shot Conversational Question Generation with Pre-trained Language ModelLong10 citations
1047. Text Augmentation Using Dataset Reconstruction for Low-Resource ClassificationFindings10 citations
1048. The Web Can Be Your Oyster for Improving Language ModelsFindings10 citations
1049. The economic trade-offs of large language models: A case studyIndustry10 citations
1050. To Revise or Not to Revise: Learning to Detect Improvable Claims for Argumentative Writing SupportLong10 citations
1051. Training Trajectories of Language Models Across ScalesLong10 citations
1052. Transformer Language Models Handle Word Frequency in Prediction HeadFindings10 citations
1053. Varta: A Large-Scale Headline-Generation Dataset for Indic LanguagesFindings10 citations
1054. WeCheck: Strong Factual Consistency Checker via Weakly Supervised LearningLong10 citations
1055. A Benchmark on Extremely Weakly Supervised Text Classification: Reconcile Seed Matching and Prompting ApproachesFindings9 citations
1056. A Cognitive Stimulation Dialogue System with Multi-source Knowledge Fusion for Elders with Cognitive ImpairmentLong9 citations
1057. A dynamic programming algorithm for span-based nested named-entity recognition in O(n2)Long9 citations
1058. AQE: Argument Quadruplet Extraction via a Quad-Tagging Augmented Generative ApproachFindings9 citations
1059. Alleviating Exposure Bias via Multi-level Contrastive Learning and Deviation Simulation in Abstractive SummarizationFindings9 citations
1060. Are Sample-Efficient NLP Models More Robust?Short9 citations
1061. Attractive Storyteller: Stylized Visual Storytelling with Unpaired TextLong9 citations
1062. BREAK: Breaking the Dialogue State Tracking Barrier with Beam Search and Re-rankingLong9 citations
1063. Boost Transformer-based Language Models with GPU-Friendly Sparsity and QuantizationFindings9 citations
1064. Breeding Machine Translations: Evolutionary approach to survive and thrive in the world of automated evaluationLong9 citations
1065. CDA: A Contrastive Data Augmentation Method for Alzheimer’s Disease DetectionFindings9 citations
1066. Can Language Models Be Specific? How?Findings9 citations
1067. Causal Intervention for Mitigating Name Bias in Machine Reading ComprehensionFindings9 citations
1068. Clustering-Aware Negative Sampling for Unsupervised Sentence RepresentationFindings9 citations
1069. Concise Answers to Complex Questions: Summarization of Long-form AnswersLong9 citations
1070. Consistency Regularization Training for Compositional GeneralizationLong9 citations
1071. Contrastive Learning with Generated Representations for Inductive Knowledge Graph EmbeddingFindings9 citations
1072. Cross-lingual Continual LearningLong9 citations
1073. Decker: Double Check with Heterogeneous Knowledge for Commonsense Fact VerificationFindings9 citations
1074. Digging out Discrimination Information from Generated Samples for Robust Visual Question AnsweringFindings9 citations
1075. DimonGen: Diversified Generative Commonsense Reasoning for Explaining Concept RelationshipsLong9 citations
1076. Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question AnsweringFindings9 citations
1077. Do Question Answering Modeling Improvements Hold Across Benchmarks?Long9 citations
1078. Dynamic and Efficient Inference for Text Generation via BERT FamilyLong9 citations
1079. ECOLA: Enhancing Temporal Knowledge Embeddings with Contextualized Language RepresentationsFindings9 citations
1080. ELQA: A Corpus of Metalinguistic Questions and Answers about EnglishLong9 citations
1081. EPIC: Multi-Perspective Annotation of a Corpus of IronyLong9 citations
1082. Early Exit with Disentangled Representation and Equiangular Tight FrameFindings9 citations
1083. Explicit Syntactic Guidance for Neural Text GenerationLong9 citations
1084. Few-shot Classification with Hypersphere Modeling of PrototypesFindings9 citations
1085. Few-shot Event Detection: An Empirical Study and a Unified ViewLong9 citations
1086. Finding the Pillars of Strength for Multi-Head AttentionLong9 citations
1087. Finding the SWEET Spot: Analysis and Improvement of Adaptive Inference in Low Resource SettingsLong9 citations
1088. GNN-SL: Sequence Labeling Based on Nearest Examples via GNNFindings9 citations
1089. Generating Deep Questions with Commonsense Reasoning Ability from the Text by Disentangled Adversarial InferenceFindings9 citations
1090. ISLTranslate: Dataset for Translating Indian Sign LanguageFindings9 citations
1091. Impact of Adversarial Training on Robustness and Generalizability of Language ModelsFindings9 citations
1092. Improved Instruction Ordering in Recipe-Grounded ConversationLong9 citations
1093. Improving Radiology Summarization with Radiograph and Anatomy PromptsFindings9 citations
1094. Improving the robustness of NLI models with minimax trainingLong9 citations
1095. Incorporating Attribution Importance for Improving Faithfulness MetricsLong9 citations
1096. Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention TrainingFindings9 citations
1097. Knowledgeable Parameter Efficient Tuning Network for Commonsense Question AnsweringLong9 citations
1098. Language Modeling with Latent SituationsFindings9 citations
1099. Learning Event-aware Measures for Event Coreference ResolutionFindings9 citations
1100. Learning to Leverage High-Order Medical Knowledge Graph for Joint Entity and Relation ExtractionFindings9 citations
1101. Learning to Substitute Spans towards Improving Compositional GeneralizationLong9 citations
1102. Learning “O” Helps for Learning More: Handling the Unlabeled Entity Problem for Class-incremental NERLong9 citations
1103. Mapping Brains with Language Models: A SurveyFindings9 citations
1104. Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language ModelsLong9 citations
1105. Measuring Intersectional Biases in Historical DocumentsFindings9 citations
1106. MoNET: Tackle State Momentum via Noise-Enhanced Training for Dialogue State TrackingFindings9 citations
1107. Modeling Structural Similarities between Documents for Coherence Assessment with Graph Convolutional NetworksLong9 citations
1108. Modeling User Satisfaction Dynamics in Dialogue via Hawkes ProcessLong9 citations
1109. Multimedia Generative Script Learning for Task PlanningFindings9 citations
1110. On Prefix-tuning for Lightweight Out-of-distribution DetectionLong9 citations
1111. Parameter-efficient Weight Ensembling Facilitates Task-level Knowledge TransferShort9 citations
1112. Plug-and-Play Document Modules for Pre-trained ModelsLong9 citations
1113. Probing Physical Reasoning with Counter-Commonsense ContextShort9 citations
1114. Question-Answering in a Low-resourced Language: Benchmark Dataset and Models for TigrinyaLong9 citations
1115. RADE: Reference-Assisted Dialogue Evaluation for Open-Domain DialogueLong9 citations
1116. Retrieval-Based Transformer for Table AugmentationFindings9 citations
1117. Revisiting Automated Prompting: Are We Actually Doing Better?Short9 citations
1118. SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity RecognitionFindings9 citations
1119. SCCS: Semantics-Consistent Cross-domain Summarization via Optimal Transport AlignmentFindings9 citations
1120. SaFER: A Robust and Efficient Framework for Fine-tuning BERT-based Classifier with Noisy LabelsIndustry9 citations
1121. Sequential Path Signature Networks for Personalised Longitudinal Language ModelingFindings9 citations
1122. Should you marginalize over possible tokenizations?Short9 citations
1123. Split-NER: Named Entity Recognition via Two Question-Answering-based ClassificationsShort9 citations
1124. Surface-Based Retrieval Reduces Perplexity of Retrieval-Augmented Language ModelsShort9 citations
1125. Synthetic Pre-Training Tasks for Neural Machine TranslationFindings9 citations
1126. The Role of Global and Local Context in Named Entity RecognitionShort9 citations
1127. Towards Generative Event Factuality PredictionFindings9 citations
1128. Towards Higher Pareto Frontier in Multilingual Machine TranslationLong9 citations
1129. USSA: A Unified Table Filling Scheme for Structured Sentiment AnalysisLong9 citations
1130. Using Collostructional Analysis to evaluate BERT’s representation of linguistic constructionsFindings9 citations
1131. VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic TransitionsLong9 citations
1132. Visually-augmented pretrained language models for NLP tasks without imagesLong9 citations
1133. What is the Real Intention behind this Question? Dataset Collection and Intention ClassificationLong9 citations
1134. What social attitudes about gender does BERT encode? Leveraging insights from psycholinguisticsLong9 citations
1135. WikiBio: a Semantic Resource for the Intersectional Analysis of Biographical EventsLong9 citations
1136. World Models for Math Story ProblemsFindings9 citations
1137. X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot AgentsFindings9 citations
1138. Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple TasksFindings9 citations
1139. Zero-Shot Prompting for Implicit Intent Prediction and Recommendation with Commonsense ReasoningFindings9 citations
1140. Zero-shot Approach to Overcome Perturbation Sensitivity of PromptsLong9 citations
1141. f-Divergence Minimization for Sequence-Level Knowledge DistillationLong9 citations
1142. A Dataset of Argumentative Dialogues on Scientific PapersLong8 citations
1143. A Method for Studying Semantic Construal in Grammatical Constructions with Interpretable Contextual Embedding SpacesLong8 citations
1144. A New Dataset and Empirical Study for Sentence Simplification in ChineseLong8 citations
1145. A Study on Knowledge Distillation from Weak Teacher for Scaling Up Pre-trained Language ModelsFindings8 citations
1146. A Study on the Efficiency and Generalization of Light Hybrid RetrieversShort8 citations
1147. AMR-TST: Abstract Meaning Representation-based Text Style TransferFindings8 citations
1148. Abstractive Text Summarization Using the BRIO Training ParadigmFindings8 citations
1149. Accurate Training of Web-based Question Answering Systems with Feedback from Ranked UsersIndustry8 citations
1150. Adaptation Approaches for Nearest Neighbor Language ModelsFindings8 citations
1151. Additive manifesto decomposition: A policy domain aware method for understanding party positioningFindings8 citations
1152. Aggregating Multiple Heuristic Signals as Supervision for Unsupervised Automated Essay ScoringLong8 citations
1153. Answering Ambiguous Questions via Iterative PromptingLong8 citations
1154. BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness MetricsLong8 citations
1155. Character Coreference Resolution in Movie ScreenplaysFindings8 citations
1156. Commonsense Knowledge Transfer for Pre-trained Language ModelsFindings8 citations
1157. DITTO: Data-efficient and Fair Targeted Subset Selection for ASR Accent AdaptationLong8 citations
1158. Data Augmentation for Low-Resource Keyphrase GenerationFindings8 citations
1159. Data-Efficient French Language Modeling with CamemBERTaFindings8 citations
1160. Debiasing Generative Named Entity Recognition by Calibrating Sequence LikelihoodShort8 citations
1161. Diable: Efficient Dialogue State Tracking as Operations on TablesFindings8 citations
1162. Disagreement Matters: Preserving Label Diversity by Jointly Modeling Item and Annotator Label Distributions with DisCoFindings8 citations
1163. Effective Contrastive Weighting for Dense Query ExpansionLong8 citations
1164. Exploiting Rich Textual User-Product Context for Improving Personalized Sentiment AnalysisFindings8 citations
1165. Exploring and Verbalizing Academic Ideas by Concept Co-occurrenceLong8 citations
1166. Exploring the Impact of Layer Normalization for Zero-shot Neural Machine TranslationShort8 citations
1167. Few-shot Low-resource Knowledge Graph Completion with Reinforced Task GenerationFindings8 citations
1168. Fixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine TranslationFindings8 citations
1169. From Characters to Words: Hierarchical Pre-trained Language Model for Open-vocabulary Language UnderstandingLong8 citations
1170. From chocolate bunny to chocolate crocodile: Do Language Models Understand Noun Compounds?Findings8 citations
1171. GEC-DePenD: Non-Autoregressive Grammatical Error Correction with Decoupled Permutation and DecodingLong8 citations
1172. GIFT: Graph-Induced Fine-Tuning for Multi-Party Conversation UnderstandingLong8 citations
1173. GRACE: Gradient-guided Controllable Retrieval for Augmenting Attribute-based Text GenerationFindings8 citations
1174. Hence, Socrates is mortal: A Benchmark for Natural Language Syllogistic ReasoningFindings8 citations
1175. Hexatagging: Projective Dependency Parsing as TaggingShort8 citations
1176. IDOL: Indicator-oriented Logic Pre-training for Logical ReasoningFindings8 citations
1177. INK: Injecting kNN Knowledge in Nearest Neighbor Machine TranslationLong8 citations
1178. Improving Automatic Quotation Attribution in Literary NovelsShort8 citations
1179. Improving Low-resource Named Entity Recognition with Graph Propagated Data AugmentationShort8 citations
1180. LAIT: Efficient Multi-Segment Encoding in Transformers with Layer-Adjustable InteractionLong8 citations
1181. Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement LearningLong8 citations
1182. Learning with Partial Annotations for Event DetectionLong8 citations
1183. MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text GenerationFindings8 citations
1184. Maximum Entropy Loss, the Silver Bullet Targeting Backdoor Attacks in Pre-trained Language ModelsFindings8 citations
1185. Multitask Pretraining with Structured Knowledge for Text-to-SQL GenerationLong8 citations
1186. Non-Sequential Graph Script Induction via Multimedia GroundingLong8 citations
1187. On “Scientific Debt” in NLP: A Case for More Rigour in Language Model Pre-Training ResearchLong8 citations
1188. OpineSum: Entailment-based self-training for abstractive opinion summarizationFindings8 citations
1189. Peer-Label Assisted Hierarchical Text ClassificationLong8 citations
1190. PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language ModelsFindings8 citations
1191. Putting Natural in Natural Language ProcessingFindings8 citations
1192. Python Code Generation by Asking Clarification QuestionsLong8 citations
1193. REV: Information-Theoretic Evaluation of Free-Text RationalesLong8 citations
1194. ReactIE: Enhancing Chemical Reaction Extraction with Weak SupervisionFindings8 citations
1195. Recyclable Tuning for Continual Pre-trainingFindings8 citations
1196. Revisiting Commonsense Reasoning in Machine Translation: Training, Evaluation and ChallengeLong8 citations
1197. Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and BeyondFindings8 citations
1198. Robustness-Aware Word Embedding Improves Certified Robustness to Adversarial Word SubstitutionsFindings8 citations
1199. SafeConv: Explaining and Correcting Conversational Unsafe BehaviorLong8 citations
1200. StoryWars: A Dataset and Instruction Tuning Baselines for Collaborative Story Understanding and GenerationLong8 citations
1201. TAPIR: Learning Adaptive Revision for Incremental Natural Language Understanding with a Two-Pass ModelFindings8 citations
1202. Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question AnsweringShort8 citations
1203. The Coreference under Transformation Labeling Dataset: Entity Tracking in Procedural Texts Using Event ModelsFindings8 citations
1204. Transfer and Active Learning for Dissonance Detection: Addressing the Rare-Class ChallengeLong8 citations
1205. Typo-Robust Representation Learning for Dense RetrievalShort8 citations
1206. UPPAM: A Unified Pre-training Architecture for Political Actor Modeling based on LanguageLong8 citations
1207. Uncertainty-Aware Bootstrap Learning for Joint Extraction on Distantly-Supervised DataShort8 citations
1208. Unsupervised Extractive Summarization of Emotion TriggersLong8 citations
1209. Weakly-Supervised Spoken Video Grounding via Semantic Interaction LearningLong8 citations
1210. What Knowledge Is Needed? Towards Explainable Memory for kNN-MT Domain AdaptationFindings8 citations
1211. When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box ScenarioFindings8 citations
1212. When and how to paraphrase for named entity recognition?Long8 citations
1213. When to Use What: An In-Depth Comparative Empirical Analysis of OpenIE Systems for Downstream ApplicationsLong8 citations
1214. With a Little Push, NLI Models can Robustly and Efficiently Predict FaithfulnessShort8 citations
1215. XDailyDialog: A Multilingual Parallel Dialogue CorpusLong8 citations
1216. Zero-shot Cross-lingual Transfer With Learned Projections Using Unlabeled Target-Language DataShort8 citations
1217. “Let’s not Quote out of Context”: Unified Vision-Language Pretraining for Context Assisted Image CaptioningIndustry8 citations
1218. A Natural Bias for Language Generation ModelsShort7 citations
1219. A Neural Divide-and-Conquer Reasoning Framework for Image Retrieval from Linguistically Complex TextLong7 citations
1220. A Simple Yet Strong Domain-Agnostic De-bias Method for Zero-Shot Sentiment ClassificationFindings7 citations
1221. A Simple, Yet Effective Approach to Finding Biases in Code GenerationFindings7 citations
1222. Adaptive Attention for Sparse-based Long-sequence TransformerFindings7 citations
1223. An Ordinal Latent Variable Model of Conflict IntensityLong7 citations
1224. AxomiyaBERTa: A Phonologically-aware Transformer Model for AssameseFindings7 citations
1225. BUCA: A Binary Classification Approach to Unsupervised Commonsense Question AnsweringShort7 citations
1226. BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine TranslationFindings7 citations
1227. Boosting Event Extraction with Denoised Structure-to-Text AugmentationFindings7 citations
1228. Boosting Transformers and Language Models for Clinical Prediction in ImmunotherapyIndustry7 citations
1229. Boosting Zero-shot Cross-lingual Retrieval by Training on Artificially Code-Switched DataFindings7 citations
1230. Bridging the Domain Gaps in Context Representations for k-Nearest Neighbor Neural Machine TranslationLong7 citations
1231. Bridging the Granularity Gap for Acoustic ModelingFindings7 citations
1232. CTC-based Non-autoregressive Speech TranslationLong7 citations
1233. CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story UnderstandingFindings7 citations
1234. CocaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image RetrievalIndustry7 citations
1235. Continual Contrastive Finetuning Improves Low-Resource Relation ExtractionLong7 citations
1236. Contrastive Novelty-Augmented Learning: Anticipating Outliers with Large Language ModelsLong7 citations
1237. Cross-Lingual Knowledge Distillation for Answer Sentence Selection in Low-Resource LanguagesFindings7 citations
1238. Cross-Lingual Transfer with Target Language-Ready Task AdaptersFindings7 citations
1239. Define, Evaluate, and Improve Task-Oriented Cognitive Capabilities for Instruction Generation ModelsFindings7 citations
1240. DialoGPS: Dialogue Path Sampling in Continuous Semantic Space for Data Augmentation in Multi-Turn ConversationsLong7 citations
1241. Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or BiasFindings7 citations
1242. Discourse-Centric Evaluation of Document-level Machine Translation with a New Densely Annotated Parallel Corpus of NovelsLong7 citations
1243. Distantly Supervised Course Concept Extraction in MOOCs with Academic DisciplineLong7 citations
1244. DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text GenerationLong7 citations
1245. Echoes from Alexandria: A Large Resource for Multilingual Book SummarizationFindings7 citations
1246. Empowering Cross-lingual Behavioral Testing of NLP Models with Typological FeaturesLong7 citations
1247. End-to-End Task-Oriented Dialogue Systems Based on SchemaFindings7 citations
1248. Enhancing Cross-lingual Transfer via Phonemic Transcription IntegrationFindings7 citations
1249. Evaluate AMR Graph Similarity via Self-supervised LearningLong7 citations
1250. Exclusive Supermask Subnetwork Training for Continual LearningFindings7 citations
1251. Exploiting Abstract Meaning Representation for Open-Domain Question AnsweringFindings7 citations
1252. Exploring Speaker-Related Information in Spoken Language Understanding for Better Speaker DiarizationFindings7 citations
1253. Extract and Attend: Improving Entity Translation in Neural Machine TranslationFindings7 citations
1254. Financial Numeric Extreme Labelling: A dataset and benchmarkingFindings7 citations
1255. FutureTOD: Teaching Future Knowledge to Pre-trained Language Model for Task-Oriented DialogueLong7 citations
1256. Generalizing Backpropagation for Gradient-Based InterpretabilityLong7 citations
1257. Gradient-Boosted Decision Tree for Listwise Context Model in Multimodal Review Helpfulness PredictionFindings7 citations
1258. HaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa LanguageFindings7 citations
1259. HiPool: Modeling Long Documents Using Graph Neural NetworksShort7 citations
1260. History repeats: Overcoming catastrophic forgetting for event-centric temporal knowledge graph completionFindings7 citations
1261. How About Kind of Generating Hedges using End-to-End Neural Models?Long7 citations
1262. How does the brain process syntactic structure while listening?Findings7 citations
1263. Importance of Synthesizing High-quality Data for Text-to-SQL ParsingFindings7 citations
1264. Improving the Detection of Multilingual Online Attacks with Rich Social Media Data from SingaporeLong7 citations
1265. Joint Constrained Learning with Boundary-adjusting for Emotion-Cause Pair ExtractionLong7 citations
1266. Joint Generator-Ranker Learning for Natural Language GenerationFindings7 citations
1267. Jointprop: Joint Semi-supervised Learning for Entity and Relation Extraction with Heterogeneous Graph-based PropagationLong7 citations
1268. Learning Dynamic Contextualised Word Embeddings via Template-based Temporal AdaptationLong7 citations
1269. Listen, Decipher and Sign: Toward Unsupervised Speech-to-Sign Language RecognitionFindings7 citations
1270. MOSPC: MOS Prediction Based on Pairwise ComparisonShort7 citations
1271. MTGP: Multi-turn Target-oriented Dialogue Guided by Generative Global Path with Flexible TurnsFindings7 citations
1272. Measuring the Effect of Influential Messages on Varying PersonasShort7 citations
1273. Meta-training with Demonstration Retrieval for Efficient Few-shot LearningFindings7 citations
1274. Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question AnsweringLong7 citations
1275. Multi-modal Sarcasm Generation: Dataset and SolutionFindings7 citations
1276. MultiTACRED: A Multilingual Version of the TAC Relation Extraction DatasetLong7 citations
1277. Neural Machine Translation for Mathematical FormulaeLong7 citations
1278. Neural Unsupervised Reconstruction of Protolanguage Word FormsLong7 citations
1279. NewsDialogues: Towards Proactive News Grounded ConversationFindings7 citations
1280. NormMark: A Weakly Supervised Markov Model for Socio-cultural Norm DiscoveryFindings7 citations
1281. On Dataset Transferability in Active Learning for TransformersFindings7 citations
1282. Optimizing Test-Time Query Representations for Dense RetrievalFindings7 citations
1283. PIP: Parse-Instructed Prefix for Syntactically Controlled Paraphrase GenerationFindings7 citations
1284. PeerDA: Data Augmentation via Modeling Peer Relation for Span Identification TasksLong7 citations
1285. PragmatiCQA: A Dataset for Pragmatic Question Answering in ConversationsFindings7 citations
1286. PromptAttack: Probing Dialogue State Trackers with Adversarial PromptsFindings7 citations
1287. Prosody-TTS: Improving Prosody with Masked Autoencoder and Conditional Diffusion Model For Expressive Text-to-SpeechFindings7 citations
1288. Pruning Pre-trained Language Models Without Fine-TuningLong7 citations
1289. QueryForm: A Simple Zero-shot Form Entity Query FrameworkFindings7 citations
1290. RadLing: Towards Efficient Radiology Report UnderstandingIndustry7 citations
1291. Reasoning over Hierarchical Question Decomposition Tree for Explainable Question AnsweringLong7 citations
1292. Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved AnnotationLong7 citations
1293. SEAG: Structure-Aware Event Causality GenerationFindings7 citations
1294. SciReviewGen: A Large-scale Dataset for Automatic Literature Review GenerationFindings7 citations
1295. Similarizing the Influence of Words with Contrastive Learning to Defend Word-level Adversarial Text AttackFindings7 citations
1296. Smart Word Suggestions for Writing AssistanceFindings7 citations
1297. StoryARG: a corpus of narratives and personal experiences in argumentative textsLong7 citations
1298. Subword Segmental Machine Translation: Unifying Segmentation and Target Sentence GenerationFindings7 citations
1299. TADA: Efficient Task-Agnostic Domain Adaptation for TransformersFindings7 citations
1300. TEPrompt: Task Enlightenment Prompt Learning for Implicit Discourse Relation RecognitionFindings7 citations
1301. TimelineQA: A Benchmark for Question Answering over TimelinesFindings7 citations
1302. To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph CompletionLong7 citations
1303. Towards Argument-Aware Abstractive Summarization of Long Legal Opinions with Summary RerankingFindings7 citations
1304. Towards Diverse and Effective Question-Answer Pair Generation from Children StorybooksFindings7 citations
1305. Towards Stable Natural Language Understanding via Information Entropy Guided DebiasingLong7 citations
1306. Training-free Neural Architecture Search for RNNs and TransformersLong7 citations
1307. TranSFormer: Slow-Fast Transformer for Machine TranslationFindings7 citations
1308. UMRSpell: Unifying the Detection and Correction Parts of Pre-trained Models towards Chinese Missing, Redundant, and Spelling CorrectionLong7 citations
1309. UniCOQE: Unified Comparative Opinion Quintuple Extraction As A SetFindings7 citations
1310. VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet MarketsLong7 citations
1311. Visual Coherence Loss for Coherent and Visually Grounded Story GenerationFindings7 citations
1312. WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span PredictionLong7 citations
1313. We Understand Elliptical Sentences, and Language Models should Too: A New Dataset for Studying Ellipsis and its Interaction with Thematic FitLong7 citations
1314. XSemPLR: Cross-Lingual Semantic Parsing in Multiple Natural Languages and Meaning RepresentationsLong7 citations
1315. xPQA: Cross-Lingual Product Question Answering in 12 LanguagesIndustry7 citations
1316. xSIM++: An Improved Proxy to Bitext Mining Performance for Low-Resource LanguagesShort7 citations
1317. A Language-First Approach for Procedure PlanningFindings6 citations
1318. A Memory Model for Question Answering from Streaming Data Supported by Rehearsal and Anticipation of Coreference InformationFindings6 citations
1319. A Simple Concatenation can Effectively Improve Speech TranslationShort6 citations
1320. A Simple and Flexible Modeling for Mental Disorder Detection by Learning from Clinical QuestionnairesLong6 citations
1321. A Survey on Zero Pronoun TranslationLong6 citations
1322. ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue SystemsLong6 citations
1323. ACROSS: An Alignment-based Framework for Low-Resource Many-to-One Cross-Lingual SummarizationFindings6 citations
1324. AUGUST: an Automatic Generation Understudy for Synthesizing Conversational Recommendation DatasetsFindings6 citations
1325. Abstractive Summarizers are Excellent Extractive SummarizersShort6 citations
1326. ActiveAED: A Human in the Loop Improves Annotation Error DetectionFindings6 citations
1327. An Extensive Exploration of Back-Translation in 60 LanguagesFindings6 citations
1328. ArgAnalysis35K : A large-scale dataset for Argument Quality AnalysisLong6 citations
1329. Aspect-aware Unsupervised Extractive Opinion SummarizationFindings6 citations
1330. AtTGen: Attribute Tree Generation for Real-World Attribute Joint ExtractionLong6 citations
1331. AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine TranslationFindings6 citations
1332. Best-k Search Algorithm for Neural Text GenerationLong6 citations
1333. Black-box language model explanation by context length probingShort6 citations
1334. Bridging the Gap between Decision and Logits in Decision-based Knowledge Distillation for Pre-trained Language ModelsLong6 citations
1335. CLIPText: A New Paradigm for Zero-shot Text ClassificationFindings6 citations
1336. Compositional Generalization without Trees using Multiset Tagging and Latent PermutationsLong6 citations
1337. Contextual Knowledge Learning for Dialogue GenerationLong6 citations
1338. Contrastive Token-Wise Meta-Learning for Unseen Performer Visual Temporal-Aligned TranslationFindings6 citations
1339. Cross-lingual Science Journalism: Select, Simplify and Rewrite Summaries for Non-expert ReadersLong6 citations
1340. DSRM: Boost Textual Adversarial Training with Distribution Shift Risk MinimizationLong6 citations
1341. DaMSTF: Domain Adversarial Learning Enhanced Meta Self-Training for Domain AdaptationLong6 citations
1342. Decoder Tuning: Efficient Language Understanding as DecodingLong6 citations
1343. Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent DiscoveryLong6 citations
1344. Diversity-Aware Coherence Loss for Improving Neural Topic ModelsShort6 citations
1345. Efficient Document Embeddings via Self-Contrastive Bregman Divergence LearningFindings6 citations
1346. Efficient Semiring-Weighted Earley ParsingLong6 citations
1347. End-to-End Argument Mining over Varying Rhetorical StructuresFindings6 citations
1348. Enhancing Few-shot Cross-lingual Transfer with Target Language Peculiar ExamplesFindings6 citations
1349. Entailment as Robust Self-LearnerLong6 citations
1350. Evaluating Paraphrastic Robustness in Textual Entailment ModelsShort6 citations
1351. Figurative Language Processing: A Linguistically Informed Feature Analysis of the Behavior of Language Models and HumansFindings6 citations
1352. Focal Training and Tagger Decouple for Grammatical Error CorrectionFindings6 citations
1353. From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation FrameworkFindings6 citations
1354. G3R: A Graph-Guided Generate-and-Rerank Framework for Complex and Cross-domain Text-to-SQL GenerationFindings6 citations
1355. Hard Sample Aware Prompt-TuningLong6 citations
1356. Hints on the data for language modeling of synthetic languages with transformersLong6 citations
1357. Images in Language Space: Exploring the Suitability of Large Language Models for Vision & Language TasksFindings6 citations
1358. In-sample Curriculum Learning by Sequence Completion for Natural Language GenerationLong6 citations
1359. Is Continuous Prompt a Combination of Discrete Prompts? Towards a Novel View for Interpreting Continuous PromptsFindings6 citations
1360. Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution DataFindings6 citations
1361. LMs stand their Ground: Investigating the Effect of Embodiment in Figurative Language Interpretation by Language ModelsFindings6 citations
1362. Layerwise universal adversarial attack on NLP modelsFindings6 citations
1363. Learning to Generalize for Cross-domain QAFindings6 citations
1364. Low-Rank Updates of pre-trained Weights for Multi-Task LearningFindings6 citations
1365. MAD-TSC: A Multilingual Aligned News Dataset for Target-dependent Sentiment ClassificationLong6 citations
1366. MTCue: Learning Zero-Shot Control of Extra-Textual Attributes by Leveraging Unstructured Context in Neural Machine TranslationFindings6 citations
1367. Multi-Row, Multi-Span Distant Supervision For Table+Text Question AnsweringLong6 citations
1368. Multimodal Prompt Learning for Product Title Generation with Extremely Limited LabelsFindings6 citations
1369. No clues good clues: out of context Lexical Relation ClassificationLong6 citations
1370. Noise-Robust Training with Dynamic Loss and Contrastive Learning for Distantly-Supervised Named Entity RecognitionFindings6 citations
1371. Not Enough Data to Pre-train Your Language Model? MT to the Rescue!Findings6 citations
1372. On Complementarity Objectives for Hybrid RetrievalLong6 citations
1373. On Evaluating Multilingual Compositional Generalization with Translated DatasetsLong6 citations
1374. PRAM: An End-to-end Prototype-based Representation Alignment Model for Zero-resource Cross-lingual Named Entity RecognitionFindings6 citations
1375. Parameter-Efficient Finetuning for Robust Continual Multilingual LearningFindings6 citations
1376. Pre-trained Personalized Review Summarization with Effective Salience EstimationFindings6 citations
1377. Predicting Customer Satisfaction with Soft Labels for Ordinal ClassificationIndustry6 citations
1378. Pretrained Bidirectional Distillation for Machine TranslationLong6 citations
1379. RAMP: Retrieval and Attribute-Marking Enhanced Prompting for Attribute-Controlled TranslationShort6 citations
1380. RC3: Regularized Contrastive Cross-lingual Cross-modal Pre-trainingFindings6 citations
1381. Reinforcement Learning for Topic ModelsFindings6 citations
1382. Rethinking Translation Memory Augmented Neural Machine TranslationFindings6 citations
1383. Retrieval-free Knowledge Injection through Multi-Document Traversal for Dialogue ModelsLong6 citations
1384. Retrieving Multimodal Prompts for Generative Visual Question AnsweringFindings6 citations
1385. Retrieving Relevant Context to Align Representations for Cross-lingual Event DetectionFindings6 citations
1386. SConE: Simplified Cone Embeddings with Symbolic Operators for Complex Logical QueriesFindings6 citations
1387. SamToNe: Improving Contrastive Loss for Dual Encoder Retrieval Models with Same Tower NegativesFindings6 citations
1388. Scene-robust Natural Language Video Localization via Learning Domain-invariant RepresentationsFindings6 citations
1389. Schema-Guided User Satisfaction Modeling for Task-Oriented DialoguesLong6 citations
1390. Segment-Level and Category-Oriented Network for Knowledge-Based Referring Expression ComprehensionFindings6 citations
1391. Sentiment Analysis using the Relationship between Users and ProductsFindings6 citations
1392. Songs Across Borders: Singable and Controllable Neural Lyric TranslationLong6 citations
1393. Span-Selective Linear Attention Transformers for Effective and Robust Schema-Guided Dialogue State TrackingLong6 citations
1394. Structure-Discourse Hierarchical Graph for Conditional Question Answering on Long DocumentsFindings6 citations
1395. Subjective Crowd Disagreements for Subjective Data: Uncovering Meaningful CrowdOpinion with Population-level LearningLong6 citations
1396. Taxonomy of Problems in Lexical SemanticsFindings6 citations
1397. Teamwork Is Not Always Good: An Empirical Study of Classifier Drift in Class-incremental Information ExtractionFindings6 citations
1398. TempLM: Distilling Language Models into Template-Based GeneratorsFindings6 citations
1399. Text Style Transfer with Contrastive Transfer Pattern MiningLong6 citations
1400. Towards Alleviating the Object Bias in Prompt Tuning-based Factual Knowledge ExtractionFindings6 citations
1401. Towards Open-Domain Twitter User Profile InferenceFindings6 citations
1402. Towards Open-World Product Attribute Mining: A Lightly-Supervised ApproachLong6 citations
1403. Towards Zero-Shot Persona Dialogue Generation with In-Context LearningFindings6 citations
1404. Trade-Offs Between Fairness and Privacy in Language ModelingFindings6 citations
1405. Transferring General Multimodal Pretrained Models to Text RecognitionFindings6 citations
1406. Trigger-Argument based Explanation for Event DetectionFindings6 citations
1407. Two-Stage Fine-Tuning for Improved Bias and Variance for Large Pretrained Language ModelsLong6 citations
1408. Understanding and Improving the Robustness of Terminology Constraints in Neural Machine TranslationLong6 citations
1409. UniLG: A Unified Structure-aware Framework for Lyrics GenerationLong6 citations
1410. Universal Information Extraction with Meta-Pretrained Self-RetrievalFindings6 citations
1411. Verifying Annotation Agreement without Multiple Experts: A Case Study with Gujarati SNACSFindings6 citations
1412. WYWEB: A NLP Evaluation Benchmark For Classical ChineseFindings6 citations
1413. What are the Desired Characteristics of Calibration Sets? Identifying Correlates on Long Form Scientific SummarizationLong6 citations
1414. When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLPLong6 citations
1415. With Prejudice to None: A Few-Shot, Multilingual Transfer Learning Approach to Detect Social Bias in Low Resource LanguagesFindings6 citations
1416. Your spouse needs professional help: Determining the Contextual Appropriateness of Messages through Modeling Social RelationshipsLong6 citations
1417. A Cautious Generalization Goes a Long Way: Learning Morphophonological RulesLong5 citations
1418. A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity RecognitionFindings5 citations
1419. A Fast Algorithm for Computing Prefix ProbabilitiesShort5 citations
1420. A Theory of Unsupervised Speech RecognitionLong5 citations
1421. A Weakly Supervised Classifier and Dataset of White Supremacist LanguageShort5 citations
1422. AI Coach Assist: An Automated Approach for Call Recommendation in Contact Centers for Agent CoachingIndustry5 citations
1423. AMRs Assemble! Learning to Ensemble with Autoregressive Models for AMR ParsingShort5 citations
1424. Ambiguity Meets Uncertainty: Investigating Uncertainty Estimation for Word Sense DisambiguationFindings5 citations
1425. Ambiguous Learning from Retrieval: Towards Zero-shot Semantic ParsingLong5 citations
1426. An Invariant Learning Characterization of Controlled Text GenerationLong5 citations
1427. Answering Unanswered Questions through Semantic Reformulations in Spoken QAIndustry5 citations
1428. AttenWalker: Unsupervised Long-Document Question Answering via Attention-based Graph WalkingFindings5 citations
1429. Automated Refugee Case Analysis: An NLP Pipeline for Supporting Legal PractitionersFindings5 citations
1430. Automatic Annotation of Direct Speech in Written French NarrativesLong5 citations
1431. Automatic Readability Assessment for Closely Related LanguagesFindings5 citations
1432. BIG-C: a Multimodal Multi-Purpose Dataset for BembaLong5 citations
1433. Balancing Lexical and Semantic Quality in Abstractive SummarizationShort5 citations
1434. Beyond Contrastive Learning: A Variational Generative Model for Multilingual RetrievalLong5 citations
1435. CFL: Causally Fair Language Models Through Token-level Attribute Controlled GenerationFindings5 citations
1436. CORE: Cooperative Training of Retriever-Reranker for Effective Dialogue Response SelectionLong5 citations
1437. CausalDialogue: Modeling Utterance-level Causality in ConversationsFindings5 citations
1438. Class-Adaptive Self-Training for Relation Extraction with Incompletely Annotated Training DataFindings5 citations
1439. CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity RecognitionLong5 citations
1440. Common Law Annotations: Investigating the Stability of Dialog System Output AnnotationsFindings5 citations
1441. Compositional Mathematical Encoding for Math Word ProblemsFindings5 citations
1442. Connectivity Patterns are Task EmbeddingsFindings5 citations
1443. Context-Aware Query Rewriting for Improving Users’ Search Experience on E-commerce WebsitesIndustry5 citations
1444. Contextual Distortion Reveals Constituency: Masked Language Models are Implicit ParsersLong5 citations
1445. Controlling Learned Effects to Reduce Spurious Correlations in Text ClassifiersLong5 citations
1446. Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected ReasoningLong5 citations
1447. Cross Encoding as Augmentation: Towards Effective Educational Text ClassificationFindings5 citations
1448. Cross-Modal Attribute Insertions for Assessing the Robustness of Vision-and-Language LearningLong5 citations
1449. Dating Greek Papyri with Text RegressionLong5 citations
1450. Dependency resolution at the syntax-semantics interface: psycholinguistic and computational insights on control dependenciesLong5 citations
1451. Detecting Contradictory COVID-19 Drug Efficacy Claims from Biomedical LiteratureShort5 citations
1452. Disentangling Aspect and Stance via a Siamese Autoencoder for Aspect Clustering of Vaccination OpinionsFindings5 citations
1453. Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning TransformersFindings5 citations
1454. Domain Incremental Lifelong Learning in an Open WorldFindings5 citations
1455. Dual Cache for Long Document Neural Coreference ResolutionLong5 citations
1456. Efficient Shapley Values Estimation by Amortization for Text ClassificationLong5 citations
1457. EmbedTextNet: Dimension Reduction with Weighted Reconstruction and Correlation Losses for Efficient Text EmbeddingFindings5 citations
1458. Entropy-guided Vocabulary Augmentation of Multilingual Language Models for Low-resource TasksFindings5 citations
1459. Envisioning Future from the Past: Hierarchical Duality Learning for Multi-Turn Dialogue GenerationLong5 citations
1460. Exploiting Hierarchically Structured Categories in Fine-grained Chinese Named Entity RecognitionFindings5 citations
1461. Exploring How Generative Adversarial Networks Learn Phonological RepresentationsLong5 citations
1462. Exploring the Capacity of Pretrained Language Models for Reasoning about Actions and ChangeLong5 citations
1463. Federated Domain Adaptation for Named Entity Recognition via Distilling with Heterogeneous Tag SetsFindings5 citations
1464. Federated Learning for Semantic Parsing: Task Formulation, Evaluation Setup, New AlgorithmsLong5 citations
1465. Fixed Input Parameterization for Efficient PromptingFindings5 citations
1466. Follow the leader(board) with confidence: Estimating p-values from a single test set with item and response varianceFindings5 citations
1467. Free Lunch: Robust Cross-Lingual Transfer via Model Checkpoint AveragingLong5 citations
1468. GUMSum: Multi-Genre Data and Evaluation for English Abstractive SummarizationFindings5 citations
1469. Generate-then-Retrieve: Intent-Aware FAQ Retrieval in Product SearchIndustry5 citations
1470. Generating Hashtags for Short-form Videos with Guided SignalsLong5 citations
1471. Generating Labeled Data for Relation Extraction: A Meta Learning Approach with Joint GPT-2 TrainingFindings5 citations
1472. Guiding Computational Stance Detection with Expanded Stance Triangle FrameworkLong5 citations
1473. Guiding Dialogue Agents to Complex Semantic Targets by Dynamically Completing Knowledge GraphFindings5 citations
1474. HeGeL: A Novel Dataset for Geo-Location from Hebrew TextFindings5 citations
1475. Helping a Friend or Supporting a Cause? Disentangling Active and Passive Cosponsorship in the U.S. CongressLong5 citations
1476. HiFi: High-Information Attention Heads Hold for Parameter-Efficient Model AdaptationLong5 citations
1477. How Many Answers Should I Give? An Empirical Study of Multi-Answer Reading ComprehensionFindings5 citations
1478. How Well Apply Simple MLP to Incomplete Utterance Rewriting?Short5 citations
1479. IDRISI-RA: The First Arabic Location Mention Recognition Dataset of Disaster TweetsLong5 citations
1480. IM-TQA: A Chinese Table Question Answering Dataset with Implicit and Multi-type Table StructuresLong5 citations
1481. Ideology Prediction from Scarce and Biased Supervision: Learn to Disregard the “What” and Focus on the “How”!Long5 citations
1482. Implicit Memory Transformer for Computationally Efficient Simultaneous Speech TranslationFindings5 citations
1483. Improving Named Entity Recognition via Bridge-based Domain AdaptationFindings5 citations
1484. Improving Pretraining Techniques for Code-Switched NLPLong5 citations
1485. Improving Translation Quality Estimation with Bias MitigationLong5 citations
1486. KAFA: Rethinking Image Ad Understanding with Knowledge-Augmented Feature Adaptation of Vision-Language ModelsIndustry5 citations
1487. LET: Leveraging Error Type Information for Grammatical Error CorrectionFindings5 citations
1488. Label Agnostic Pre-training for Zero-shot Text ClassificationFindings5 citations
1489. Label efficient semi-supervised conversational intent classificationIndustry5 citations
1490. Language of BargainingLong5 citations
1491. Learning Action Conditions from Instructional Manuals for Instruction UnderstandingLong5 citations
1492. Learning Answer Generation using Supervision from Automatic Question Answering EvaluatorsLong5 citations
1493. Learning to Predict Persona Information for Dialogue Personalization without Explicit Persona DescriptionFindings5 citations
1494. MEMEX: Detecting Explanatory Evidence for Memes via Knowledge-Enriched ContextualizationLong5 citations
1495. ManagerTower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation LearningLong5 citations
1496. Modality Adaption or Regularization? A Case Study on End-to-End Speech TranslationShort5 citations
1497. Modularized Zero-shot VQA with Pre-trained ModelsFindings5 citations
1498. Morphological Inflection: A Reality CheckLong5 citations
1499. Multi-Domain Dialogue State Tracking with Disentangled Domain-Slot AttentionFindings5 citations
1500. Multilingual Event Extraction from Historical Newspaper AdvertsLong5 citations
1501. Multilingual Knowledge Graph Completion with Language-Sensitive Multi-Graph AttentionLong5 citations
1502. NEUROSTRUCTURAL DECODING: Neural Text Generation with Structural ConstraintsLong5 citations
1503. On Degrees of Freedom in Defining and Testing Natural Language UnderstandingFindings5 citations
1504. PMI-Align: Word Alignment With Point-Wise Mutual Information Without Requiring Parallel Training DataFindings5 citations
1505. PV2TEA: Patching Visual Modality to Textual-Established Information ExtractionFindings5 citations
1506. PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational MechanismLong5 citations
1507. Parallel Data Helps Neural Entity Coreference ResolutionFindings5 citations
1508. Phrase Retrieval for Open Domain Conversational Question Answering with Conversational Dependency Modeling via Contrastive LearningFindings5 citations
1509. Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation LearningLong5 citations
1510. Pragmatic Inference with a CLIP Listener for Contrastive CaptioningFindings5 citations
1511. Prompt Tuning for Unified Multimodal Pretrained ModelsFindings5 citations
1512. Prototype-Based Interpretability for Legal Citation PredictionFindings5 citations
1513. Real-World Compositional Generalization with Disentangled Sequence-to-Sequence LearningFindings5 citations
1514. Reimagining Retrieval Augmented Language Models for Answering QueriesFindings5 citations
1515. Reinforced Active Learning for Low-Resource, Domain-Specific, Multi-Label Text ClassificationFindings5 citations
1516. Response-conditioned Turn-taking PredictionFindings5 citations
1517. Responsibility Perspective Transfer for Italian Femicide NewsFindings5 citations
1518. Revisiting Sample Size Determination in Natural Language UnderstandingFindings5 citations
1519. Revisiting Sentence Union Generation as a Testbed for Text ConsolidationFindings5 citations
1520. SETI: Systematicity Evaluation of Textual InferenceFindings5 citations
1521. SIMMC-VR: A Task-oriented Multimodal Dialog Dataset with Situated and Immersive VR StreamsLong5 citations
1522. SPEECH: Structured Prediction with Energy-Based Event-Centric HyperspheresLong5 citations
1523. SPM: A Split-Parsing Method for Joint Multi-Intent Detection and Slot FillingIndustry5 citations
1524. Search Query Spell Correction with Weak Supervision in E-commerceIndustry5 citations
1525. Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue GenerationLong5 citations
1526. Semantic-conditioned Dual Adaptation for Cross-domain Query-based Visual SegmentationFindings5 citations
1527. Semi-Supervised Domain Adaptation for Emotion-Related TasksFindings5 citations
1528. So many design choices: Improving and interpreting neural agent communication in signaling gamesFindings5 citations
1529. StructSP: Efficient Fine-tuning of Task-Oriented Dialog System by Using Structure-aware Boosting and Grammar ConstraintsFindings5 citations
1530. Stubborn Lexical Bias in Data and ModelsFindings5 citations
1531. Test-time Adaptation for Machine Translation Evaluation by Uncertainty MinimizationLong5 citations
1532. To Adapt or to Annotate: Challenges and Interventions for Domain Adaptation in Open-Domain Question AnsweringLong5 citations
1533. Token-wise Decomposition of Autoregressive Language Model Hidden States for Analyzing Model PredictionsLong5 citations
1534. Towards Better Entity Linking with Multi-View Enhanced DistillationLong5 citations
1535. Towards Domain-Agnostic and Domain-Adaptive Dementia Detection from Spoken LanguageLong5 citations
1536. Towards Fewer Hallucinations in Knowledge-Grounded Dialogue Generation via Augmentative and Contrastive Knowledge-DialogueShort5 citations
1537. Towards Identifying Fine-Grained Depression Symptoms from MemesLong5 citations
1538. Towards Reference-free Text Simplification Evaluation with a BERT Siamese Network ArchitectureFindings5 citations
1539. Tucker Decomposition with Frequency Attention for Temporal Knowledge Graph CompletionFindings5 citations
1540. UMSE: Unified Multi-scenario Summarization EvaluationFindings5 citations
1541. Uncovering and Categorizing Social Biases in Text-to-SQLLong5 citations
1542. Uni-Encoder: A Fast and Accurate Response Selection Paradigm for Generation-Based Dialogue SystemsFindings5 citations
1543. Unified Contextual Query RewritingIndustry5 citations
1544. Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft LogicLong5 citations
1545. When to Read Documents or QA History: On Unified and Selective Open-domain QAFindings5 citations
1546. Zero-Shot Classification by Logical Reasoning on Natural Language ExplanationsFindings5 citations
1547. “A Little is Enough”: Few-Shot Quality Estimation based Corpus Filtering improves Machine TranslationFindings5 citations
1548. A Class-Rebalancing Self-Training Framework for Distantly-Supervised Named Entity RecognitionFindings4 citations
1549. A Set Prediction Network For Extractive SummarizationFindings4 citations
1550. Adaptive Ordered Information Extraction with Deep Reinforcement LearningFindings4 citations
1551. Adversarial Training for Low-Resource Disfluency CorrectionFindings4 citations
1552. AlignSTS: Speech-to-Singing Conversion via Cross-Modal AlignmentFindings4 citations
1553. An Integrated Approach for Political Bias Prediction and Explanation Based on Discursive StructureFindings4 citations
1554. AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis TasksFindings4 citations
1555. Are Pre-trained Language Models Useful for Model Ensemble in Chinese Grammatical Error Correction?Short4 citations
1556. Asymmetric feature interaction for interpreting model predictionsFindings4 citations
1557. Attribute Controlled Dialogue PromptingFindings4 citations
1558. Automatic Creation of Named Entity Recognition Datasets by Querying Phrase RepresentationsLong4 citations
1559. Back to Patterns: Efficient Japanese Morphological Analysis with Feature-Sequence TrieShort4 citations
1560. Balancing the Effect of Training Dataset Distribution of Multiple Styles for Multi-Style Text TransferFindings4 citations
1561. CASN:Class-Aware Score Network for Textual Adversarial DetectionLong4 citations
1562. CLCL: Non-compositional Expression Detection with Contrastive Learning and Curriculum LearningLong4 citations
1563. Characterizing the Impacts of Instances on RobustnessFindings4 citations
1564. Chemical Language Understanding BenchmarkIndustry4 citations
1565. ClaimDiff: Comparing and Contrasting Claims on Contentious IssuesFindings4 citations
1566. Clinical Note Owns its Hierarchy: Multi-Level Hypergraph Neural Networks for Patient-Level Representation LearningLong4 citations
1567. Coherent or Not? Stressing a Neural Language Model for Discourse Coherence in Multiple LanguagesFindings4 citations
1568. Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation ExtractionFindings4 citations
1569. Context-Aware Transformer Pre-Training for Answer Sentence SelectionShort4 citations
1570. Contrastive Learning with Adversarial Examples for Alleviating Pathology of Language ModelLong4 citations
1571. Controlled Text Generation with Hidden Representation TransformationsFindings4 citations
1572. Curriculum Learning for Graph Neural Networks: A Multiview Competence-based ApproachLong4 citations
1573. Debiasing should be Good and Bad: Measuring the Consistency of Debiasing Techniques in Language ModelsFindings4 citations
1574. Decoding Symbolism in Language ModelsLong4 citations
1575. DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question AnsweringLong4 citations
1576. Denoising Enhanced Distantly Supervised Ultrafine Entity TypingFindings4 citations
1577. Detecting Adversarial Samples through Sharpness of Loss LandscapeFindings4 citations
1578. Disambiguated Lexically Constrained Neural Machine TranslationFindings4 citations
1579. Disentangling Text Representation With Counter-Template For Unsupervised Opinion SummarizationFindings4 citations
1580. Disfluency Generation for More Robust Dialogue SystemsFindings4 citations
1581. DivHSK: Diverse Headline Generation using Self-Attention based Keyword SelectionFindings4 citations
1582. Do I have the Knowledge to Answer? Investigating Answerability of Knowledge Base QuestionsLong4 citations
1583. Don’t Parse, Choose Spans! Continuous and Discontinuous Constituency Parsing via Autoregressive Span SelectionLong4 citations
1584. Duplex Diffusion Models Improve Speech-to-Speech TranslationFindings4 citations
1585. Eliciting Affective Events from Language Models by Multiple View Co-promptingFindings4 citations
1586. Enhancing Language Representation with Constructional Information for Natural Language UnderstandingLong4 citations
1587. Evaluating pragmatic abilities of image captioners on A3DSShort4 citations
1588. Exploring Non-Verbal Predicates in Semantic Role Labeling: Challenges and OpportunitiesFindings4 citations
1589. Exploring the Impact of Vision Features in News Image CaptioningFindings4 citations
1590. FAA: Fine-grained Attention Alignment for Cascade Document RankingLong4 citations
1591. Factual or Contextual? Disentangling Error Types in Entity Description GenerationLong4 citations
1592. Few-shot Adaptation Works with UnpredicTable DataLong4 citations
1593. Focusing, Bridging and Prompting for Few-shot Nested Named Entity RecognitionFindings4 citations
1594. Foveate, Attribute, and Rationalize: Towards Physically Safe and Trustworthy AIFindings4 citations
1595. Geo-Seq2seq: Twitter User Geolocation on Noisy Data through Sequence to Sequence LearningFindings4 citations
1596. Graph-based Relation Mining for Context-free Out-of-vocabulary Word Embedding LearningLong4 citations
1597. HermEs: Interactive Spreadsheet Formula Prediction via Hierarchical Formulet ExpansionLong4 citations
1598. Hidden Schema NetworksLong4 citations
1599. HuCurl: Human-induced Curriculum DiscoveryLong4 citations
1600. HuaSLIM: Human Attention Motivated Shortcut Learning Identification and Mitigation for Large Language modelsFindings4 citations
1601. HyHTM: Hyperbolic Geometry-based Hierarchical Topic ModelFindings4 citations
1602. I run as fast as a rabbit, can you? A Multilingual Simile Dialogues DatasetsFindings4 citations
1603. Improving Language Model Integration for Neural Machine TranslationFindings4 citations
1604. Incomplete Utterance Rewriting by A Two-Phase Locate-and-Fill RegimeFindings4 citations
1605. Incorporating Factuality Inference to Identify Document-level Event FactualityFindings4 citations
1606. InfoSync: Information Synchronization across Multilingual Semi-structured TablesFindings4 citations
1607. Injecting knowledge into language generation: a case study in auto-charting after-visit care instructions from medical dialogueLong4 citations
1608. Introducing Semantics into Speech EncodersLong4 citations
1609. Jointly Reparametrized Multi-Layer Adaptation for Efficient and Private TuningFindings4 citations
1610. KNOW How to Make Up Your Mind! Adversarially Detecting and Alleviating Inconsistencies in Natural Language ExplanationsShort4 citations
1611. KNSE: A Knowledge-aware Natural Language Inference Framework for Dialogue Symptom Status RecognitionFindings4 citations
1612. LI-RAGE: Late Interaction Retrieval Augmented Generation with Explicit Signals for Open-Domain Table Question AnsweringShort4 citations
1613. Large Language Models Are Partially Primed in Pronoun InterpretationFindings4 citations
1614. Leveraging Denoised Abstract Meaning Representation for Grammatical Error CorrectionFindings4 citations
1615. MISMATCH: Fine-grained Evaluation of Machine-generated Text with Mismatch Error TypesFindings4 citations
1616. Masked Latent Semantic Modeling: an Efficient Pre-training Alternative to Masked Language ModelingFindings4 citations
1617. Measuring Consistency in Text-based Financial Forecasting ModelsLong4 citations
1618. Measuring and Mitigating Local Instability in Deep Neural NetworksFindings4 citations
1619. Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient InferenceFindings4 citations
1620. Multi-Relational Probabilistic Event Representation Learning via Projected Gaussian EmbeddingFindings4 citations
1621. Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge ConstraintsFindings4 citations
1622. Multilingual Sequence-to-Sequence Models for Hebrew NLPFindings4 citations
1623. Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and BenchmarkFindings4 citations
1624. NLP Reproducibility For All: Understanding Experiences of BeginnersLong4 citations
1625. Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model ControlFindings4 citations
1626. NarrowBERT: Accelerating Masked Language Model Pretraining and InferenceShort4 citations
1627. NatLogAttack: A Framework for Attacking Natural Language Inference Models with Natural LogicLong4 citations
1628. Neighboring Words Affect Human Interpretation of Saliency ExplanationsFindings4 citations
1629. Node Placement in Argument Maps: Modeling Unidirectional Relations in High & Low-Resource ScenariosLong4 citations
1630. Open-World Factually Consistent Question GenerationFindings4 citations
1631. Query Enhanced Knowledge-Intensive Conversation via Unsupervised Joint ModelingLong4 citations
1632. Race, Gender, and Age Biases in Biomedical Masked Language ModelsFindings4 citations
1633. Rapid Diffusion: Building Domain-Specific Text-to-Image Synthesizers with Fast Inference SpeedIndustry4 citations
1634. Resolving Indirect Referring Expressions for Entity SelectionLong4 citations
1635. Sampling Better Negatives for Distantly Supervised Named Entity RecognitionFindings4 citations
1636. Scaling Laws for BERT in Low-Resource SettingsFindings4 citations
1637. Sentence Ordering with a Coherence VerifierFindings4 citations
1638. Separating Context and Pattern: Learning Disentangled Sentence Representations for Low-Resource Extractive SummarizationFindings4 citations
1639. Silver Syntax Pre-training for Cross-Domain Relation ExtractionFindings4 citations
1640. SkillQG: Learning to Generate Question for Reading Comprehension AssessmentFindings4 citations
1641. Soft Language Clustering for Multilingual Model Pre-trainingLong4 citations
1642. Temporal Relation Classification using Boolean Question AnsweringFindings4 citations
1643. The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active LearningLong4 citations
1644. Theory-Grounded Computational Text AnalysisShort4 citations
1645. Tokenization with Factorized Subword EncodingFindings4 citations
1646. Topic and Style-aware Transformer for Multimodal Emotion RecognitionFindings4 citations
1647. Towards Accurate Translation via Semantically Appropriate Application of Lexical ConstraintsFindings4 citations
1648. Towards Distribution-shift Robust Text Classification of Emotional ContentFindings4 citations
1649. Transferable and Efficient: Unifying Dynamic Multi-Domain Product CategorizationIndustry4 citations
1650. Understanding the Cooking Process with English Recipe TextFindings4 citations
1651. Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive GrammarsLong4 citations
1652. Unsupervised Selective Rationalization with Noise InjectionLong4 citations
1653. Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss InformationLong4 citations
1654. What is the best recipe for character-level encoder-only modelling?Long4 citations
1655. Word sense extensionLong4 citations
1656. XtremeCLIP: Extremely Parameter-efficient Tuning for Low-resource Vision Language UnderstandingFindings4 citations
1657. ZeroAE: Pre-trained Language Model based Autoencoder for Transductive Zero-shot Text ClassificationFindings4 citations
1658. “Knowledge is Power”: Constructing Knowledge Graph of Abdominal Organs and Using Them for Automatic Radiology Report GenerationIndustry4 citations
1659. A Compare-and-contrast Multistage Pipeline for Uncovering Financial Signals in Financial ReportsLong3 citations
1660. A Diffusion Model for Event Skeleton GenerationFindings3 citations
1661. A Hierarchical Explanation Generation Method Based on Feature Interaction DetectionFindings3 citations
1662. A Statistical Exploration of Text Partition Into Constituents: The Case of the Priestly Source in the Books of Genesis and ExodusFindings3 citations
1663. A Textual Dataset for Situated Proactive Response SelectionLong3 citations
1664. Advancing Multi-Criteria Chinese Word Segmentation Through Criterion Classification and DenoisingLong3 citations
1665. Align-then-Enhance: Multilingual Entailment Graph Enhancement with Soft Predicate AlignmentFindings3 citations
1666. BLOCSUM: Block Scope-based Source Code Summarization via Shared Block RepresentationFindings3 citations
1667. Bi-level Finetuning with Task-dependent Similarity Structure for Low-resource TrainingFindings3 citations
1668. Boosting Text Augmentation via Hybrid Instance Filtering FrameworkFindings3 citations
1669. Bring More Attention to Syntactic Symmetry for Automatic Postediting of High-Quality Machine TranslationsShort3 citations
1670. CELDA: Leveraging Black-box Language Model as Enhanced Classifier without LabelsLong3 citations
1671. Can Language Models Make Fun? A Case Study in Chinese Comical CrosstalkLong3 citations
1672. Class Lifelong Learning for Intent Detection via Structure Consolidation NetworksFindings3 citations
1673. Constructing Procedural Graphs with Multiple Dependency Relations: A New Dataset and BaselineFindings3 citations
1674. Contrastive Learning of Sociopragmatic Meaning in Social MediaFindings3 citations
1675. Controllable Conversation Generation with Conversation Structures via Diffusion ModelsFindings3 citations
1676. Counterfactual Probing for the Influence of Affect and Specificity on Intergroup BiasFindings3 citations
1677. Cross-Domain Argument Quality EstimationFindings3 citations
1678. Cross-lingual AMR Aligner: Paying Attention to Cross-AttentionFindings3 citations
1679. DEnsity: Open-domain Dialogue Evaluation Metric using Density EstimationFindings3 citations
1680. DMLM: Descriptive Masked Language ModelingFindings3 citations
1681. Dialog-Post: Multi-Level Self-Supervised Objectives and Hierarchical Model for Dialogue Post-TrainingLong3 citations
1682. Distilling Efficient Language-Specific Models for Cross-Lingual TransferFindings3 citations
1683. Domain Aligned Prefix Averaging for Domain Generalization in Abstractive SummarizationFindings3 citations
1684. Domain Generalization via Switch Knowledge Distillation for Robust Review RepresentationFindings3 citations
1685. DynaMiTE: Discovering Explosive Topic Evolutions with User GuidanceFindings3 citations
1686. Dynamic Regularization in UDA for Transformers in Multimodal ClassificationLong3 citations
1687. Enhancing Cross-lingual Prompting with Dual Prompt AugmentationFindings3 citations
1688. Enhancing Out-of-Vocabulary Estimation with Subword AttentionFindings3 citations
1689. Evaluating Factuality in Cross-lingual SummarizationFindings3 citations
1690. ExplainMeetSum: A Dataset for Explainable Meeting Summarization Aligned with Human IntentLong3 citations
1691. Exploiting Commonsense Knowledge about Objects for Visual Activity RecognitionFindings3 citations
1692. Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence SimilarityFindings3 citations
1693. Exploring Robust Overfitting for Pre-trained Language ModelsFindings3 citations
1694. Fantastic Expressions and Where to Find Them: Chinese Simile Generation with Multiple ConstraintsLong3 citations
1695. Few Shot Rationale Generation using Self-Training with Dual TeachersFindings3 citations
1696. Free Lunch for Efficient Textual Commonsense Integration in Language ModelsLong3 citations
1697. From Ultra-Fine to Fine: Fine-tuning Ultra-Fine Entity Typing Models to Fine-grainedLong3 citations
1698. GVdoc - Graph-based Visual DOcument ClassificationFindings3 citations
1699. Gradient Ascent Post-training Enhances Language Model GeneralizationShort3 citations
1700. Grounding the Lexical Substitution Task in EntailmentFindings3 citations
1701. HAUSER: Towards Holistic and Automatic Evaluation of Simile GenerationLong3 citations
1702. Holistic Prediction on a Time-Evolving Attributed GraphLong3 citations
1703. I am PsyAM: Modeling Happiness with Cognitive Appraisal DimensionsFindings3 citations
1704. Improving Classroom Dialogue Act Recognition from Limited Labeled Data with Self-Supervised Contrastive Learning ClassifiersFindings3 citations
1705. Improving Diachronic Word Sense Induction with a Nonparametric Bayesian methodFindings3 citations
1706. In and Out-of-Domain Text Adversarial Robustness via Label SmoothingShort3 citations
1707. Incomplete Utterance Rewriting as Sequential Greedy TaggingFindings3 citations
1708. Injecting Comparison Skills in Task-Oriented Dialogue Systems for Database Search Results DisambiguationFindings3 citations
1709. It is a Bird Therefore it is a Robin: On BERT’s Internal Consistency Between Hypernym Knowledge and Logical WordsFindings3 citations
1710. Joint End-to-end Semantic Proto-role LabelingShort3 citations
1711. K-pop and fake facts: from texts to smart alerting for maritime securityIndustry3 citations
1712. Kanbun-LM: Reading and Translating Classical Chinese in Japanese Methods by Language ModelsFindings3 citations
1713. Knowing-how & Knowing-that: A New Task for Machine Comprehension of User ManualsFindings3 citations
1714. LEDA: a Large-Organization Email-Based Decision-Dialogue-Act Analysis DatasetFindings3 citations
1715. Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic ParsingLong3 citations
1716. Learning Non-linguistic Skills without Sacrificing Linguistic ProficiencyLong3 citations
1717. Learning to Rank Utterances for Query-Focused Meeting SummarizationFindings3 citations
1718. Leveraging Prefix Transfer for Multi-Intent Text RevisionShort3 citations
1719. MIReAD: Simple Method for Learning High-quality Representations from Scientific DocumentsShort3 citations
1720. MedNgage: A Dataset for Understanding Engagement in Patient-Nurse ConversationsFindings3 citations
1721. Modeling Instance Interactions for Joint Information Extraction with Neural High-Order Conditional Random FieldLong3 citations
1722. Multilingual Pre-training with Self-supervision from Global Co-occurrence InformationFindings3 citations
1723. Negation Scope Refinement via Boundary Shift LossFindings3 citations
1724. Neural Topic Modeling based on Cycle Adversarial Training and Contrastive LearningFindings3 citations
1725. On Search Strategies for Document-Level Neural Machine TranslationFindings3 citations
1726. On the Interpretability and Significance of Bias Metrics in Texts: a PMI-based ApproachShort3 citations
1727. Open Set Relation Extraction via Unknown-Aware TrainingLong3 citations
1728. Pre-training Multi-party Dialogue Models with Latent Discourse InferenceLong3 citations
1729. Prediction and Calibration: Complex Reasoning over Knowledge Graph with Bi-directional Directed Acyclic Graph Neural NetworkFindings3 citations
1730. Probing Graph Decomposition for Argument Pair ExtractionFindings3 citations
1731. Pruning Pre-trained Language Models with Principled Importance and Self-regularizationFindings3 citations
1732. Pseudo Outlier Exposure for Out-of-Distribution Detection using Pretrained TransformersFindings3 citations
1733. Recall, Expand, and Multi-Candidate Cross-Encode: Fast and Accurate Ultra-Fine Entity TypingLong3 citations
1734. Reducing Sensitivity on Speaker Names for Text Generation from DialoguesFindings3 citations
1735. Rethinking Dictionaries and Glyphs for Chinese Language Pre-trainingFindings3 citations
1736. Rethinking the Word-level Quality Estimation for Machine Translation from Human JudgementFindings3 citations
1737. Retrieval-augmented Video Encoding for Instructional CaptioningFindings3 citations
1738. Revisiting Non-Autoregressive Translation at ScaleFindings3 citations
1739. Scale-Invariant Infinite Hierarchical Topic ModelFindings3 citations
1740. Script Normalization for Unconventional Writing of Under-Resourced Languages in Bilingual CommunitiesLong3 citations
1741. Self-Distilled Quantization: Achieving High Compression Rates in Transformer-Based Language ModelsShort3 citations
1742. SenteCon: Leveraging Lexicons to Learn Human-Interpretable Language RepresentationsFindings3 citations
1743. Structural Contrastive Pretraining for Cross-Lingual ComprehensionFindings3 citations
1744. TACR: A Table Alignment-based Cell Selection Method for HybridQAFindings3 citations
1745. Tab-CQA: A Tabular Conversational Question Answering Dataset on Financial ReportsIndustry3 citations
1746. Tab-Cleaner: Weakly Supervised Tabular Data Cleaning via Pre-training for E-commerce CatalogIndustry3 citations
1747. Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script GenerationFindings3 citations
1748. Teacher and Student Models of Offensive Language in Social MediaFindings3 citations
1749. Text Generation Model Enhanced with Semantic Information in Aspect Category Sentiment AnalysisFindings3 citations
1750. TextVerifier: Robustness Verification for Textual Classifiers with Certifiable GuaranteesFindings3 citations
1751. The Role of Output Vocabulary in T2T LMs for SPARQL Semantic ParsingFindings3 citations
1752. The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained DecodingFindings3 citations
1753. Topic-Guided Self-Introduction Generation for Social Media UsersFindings3 citations
1754. Toward Interactive DictationLong3 citations
1755. Toward More Accurate and Generalizable Evaluation Metrics for Task-Oriented DialogsIndustry3 citations
1756. Towards Understanding Omission in Dialogue SummarizationLong3 citations
1757. Tracing Linguistic Markers of Influence in a Large Online OrganisationShort3 citations
1758. Transcribing Vocal Communications of Domestic Shiba lnu DogsFindings3 citations
1759. Transitioning from benchmarks to a real-world case of information-seeking in Scientific PublicationsFindings3 citations
1760. Triggering Multi-Hop Reasoning for Question Answering in Language Models using Soft Prompts and Random WalksFindings3 citations
1761. UniEvent: Unified Generative Model with Multi-Dimensional Prefix for Zero-Shot Event-Relational ReasoningLong3 citations
1762. Unsupervised Graph-Text Mutual Conversion with a Unified Pretrained Language ModelLong3 citations
1763. Unsupervised Subtitle Segmentation with Masked Language ModelsShort3 citations
1764. Unsupervised Summarization Re-rankingFindings3 citations
1765. Weighted Contrastive Learning With False Negative Control to Help Long-tailed Product ClassificationIndustry3 citations
1766. What does the Failure to Reason with “Respectively” in Zero/Few-Shot Settings Tell Us about Language Models?Long3 citations
1767. bgGLUE: A Bulgarian General Language Understanding Evaluation BenchmarkLong3 citations
1768. mPMR: A Multilingual Pre-trained Machine Reader at ScaleShort3 citations
1769. A Holistic Approach to Reference-Free Evaluation of Machine TranslationShort2 citations
1770. A New Task and Dataset on Detecting Attacks on Human Rights DefendersFindings2 citations
1771. A Pilot Study on Dialogue-Level Dependency Parsing for ChineseFindings2 citations
1772. A Self-Supervised Integration Method of Pretrained Language Models and Word DefinitionsFindings2 citations
1773. A Unified Knowledge Graph Augmentation Service for Boosting Domain-specific NLP TasksFindings2 citations
1774. AVEN-GR: Attribute Value Extraction and Normalization using product GRaphsIndustry2 citations
1775. Acquiring Frame Element Knowledge with Deep Metric Learning for Semantic Frame InductionFindings2 citations
1776. An Exploratory Study on Model Compression for Text-to-SQLFindings2 citations
1777. Analyzing and Reducing the Performance Gap in Cross-Lingual Transfer with Fine-tuning Slow and FastLong2 citations
1778. Application-Agnostic Language Modeling for On-Device ASRIndustry2 citations
1779. Are Intermediate Layers and Labels Really Necessary? A General Language Model Distillation MethodFindings2 citations
1780. Assessing Word Importance Using Models Trained for Semantic TasksFindings2 citations
1781. Automatic Named Entity Obfuscation in SpeechFindings2 citations
1782. Bootstrapping Neural Relation and Explanation ClassifiersShort2 citations
1783. CATS: A Pragmatic Chinese Answer-to-Sequence Dataset with Large Scale and High QualityLong2 citations
1784. CIF-PT: Bridging Speech and Text Representations for Spoken Language Understanding via Continuous Integrate-and-Fire Pre-TrainingFindings2 citations
1785. COGEN: Abductive Commonsense Language GenerationShort2 citations
1786. CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical DatasetFindings2 citations
1787. Causal Matching with Text Embeddings: A Case Study in Estimating the Causal Effects of Peer Review PoliciesFindings2 citations
1788. Characterizing and Measuring Linguistic Dataset DriftLong2 citations
1789. Class based Influence Functions for Error DetectionShort2 citations
1790. CoMave: Contrastive Pre-training with Multi-scale Masking for Attribute Value ExtractionFindings2 citations
1791. Code-Switched Text Synthesis in Unseen Language PairsFindings2 citations
1792. Consistent Text Categorization using Data Augmentation in e-CommerceIndustry2 citations
1793. Constrained Policy Optimization for Controlled Self-Learning in Conversational AI SystemsIndustry2 citations
1794. Contextualized Semantic Distance between Highly Overlapped TextsFindings2 citations
1795. Contrastive Training Improves Zero-Shot Classification of Semi-structured DocumentsFindings2 citations
1796. Correction of Errors in Preference Ratings from Automated Metrics for Text GenerationFindings2 citations
1797. Covering Uncommon Ground: Gap-Focused Question Generation for Answer AssessmentShort2 citations
1798. Curating Datasets for Better Performance with Example Training DynamicsFindings2 citations
1799. DAMP: Doubly Aligned Multilingual Parser for Task-Oriented DialogueLong2 citations
1800. Deep Equilibrium Non-Autoregressive Sequence LearningFindings2 citations
1801. Deep Model Compression Also Helps Models Capture AmbiguityLong2 citations
1802. Detection and Mitigation of the Negative Impact of Dataset Extractivity on Abstractive SummarizationFindings2 citations
1803. DiMS: Distilling Multiple Steps of Iterative Non-Autoregressive Transformers for Machine TranslationFindings2 citations
1804. Distributed Marker Representation for Ambiguous Discourse Markers and Entangled RelationsLong2 citations
1805. ECG-QALM: Entity-Controlled Synthetic Text Generation using Contextual Q&A for NERFindings2 citations
1806. Easy Guided Decoding in Providing Suggestions for Interactive Machine TranslationLong2 citations
1807. Efficient Diagnosis Assignment Using Unstructured Clinical NotesShort2 citations
1808. Ellipsis-Dependent Reasoning: a New Challenge for Large Language ModelsShort2 citations
1809. Emotion Cause Extraction on Social Media without Human AnnotationFindings2 citations
1810. Encoder and Decoder, Not One Less for Pre-trained Language Model Sponsored NMTFindings2 citations
1811. Evaluation of Question Generation Needs More ReferencesFindings2 citations
1812. Event-Centric Query Expansion in Web SearchIndustry2 citations
1813. EventOA: An Event Ontology Alignment Benchmark Based on FrameNet and WikidataFindings2 citations
1814. Explanation Regeneration via Information BottleneckFindings2 citations
1815. Exploring Schema Generalizability of Text-to-SQLFindings2 citations
1816. Exploring the Compositional Generalization in Context Dependent Text-to-SQL ParsingFindings2 citations
1817. FERMAT: An Alternative to Accuracy for Numerical ReasoningLong2 citations
1818. From the One, Judge of the Whole: Typed Entailment Graph Construction with Predicate GenerationLong2 citations
1819. Fusion or Defusion? Flexible Vision-and-Language Pre-TrainingFindings2 citations
1820. G-Tuning: Improving Generalization of Pre-trained Language Models with Generative Adversarial NetworkFindings2 citations
1821. Grammar-based Decoding for Improved Compositional Generalization in Semantic ParsingFindings2 citations
1822. History Semantic Graph Enhanced Conversational KBQA with Temporal Information ModelingLong2 citations
1823. HonestBait: Forward References for Attractive but Faithful Headline GenerationFindings2 citations
1824. How does the task complexity of masked pretraining objectives affect downstream performance?Findings2 citations
1825. How effective is machine translation on low-resource code-switching? A case study comparing human and automatic metricsFindings2 citations
1826. Human Inspired Progressive Alignment and Comparative Learning for Grounded Word AcquisitionLong2 citations
1827. Hunt for Buried Treasures: Extracting Unclaimed Embodiments from Patent SpecificationsIndustry2 citations
1828. Hybrid and Collaborative Passage RerankingFindings2 citations
1829. Hypothetical Training for Robust Machine Reading Comprehension of Tabular ContextFindings2 citations
1830. Improving Autoregressive Grammatical Error Correction with Non-autoregressive ModelsFindings2 citations
1831. Improving Cross-task Generalization of Unified Table-to-text Models with Compositional Task ConfigurationsFindings2 citations
1832. Improving Syntactic Probing Correctness and Robustness with Control TasksShort2 citations
1833. Interpreting Positional Information in Perspective of Word OrderLong2 citations
1834. Investigating the Saliency of Sentiment Expressions in Aspect-Based Sentiment AnalysisFindings2 citations
1835. K-UniMorph: Korean Universal Morphology and its Feature SchemaFindings2 citations
1836. Knowledge Graph Embeddings using Neural Ito Process: From Multiple Walks to Stochastic TrajectoriesFindings2 citations
1837. LR-Sum: Summarization for Less-Resourced LanguagesFindings2 citations
1838. LaSQuE: Improved Zero-Shot Classification from Explanations Through Quantifier Modeling and Curriculum LearningFindings2 citations
1839. Learning Query Adaptive Anchor Representation for Inductive Relation PredictionFindings2 citations
1840. Learning from Children: Improving Image-Caption Pretraining via CurriculumFindings2 citations
1841. Let Me Check the Examples: Enhancing Demonstration Learning via Explicit ImitationShort2 citations
1842. Leveraging Synthetic Targets for Machine TranslationFindings2 citations
1843. Local Temperature Beam Search: Avoid Neural Text DeGeneration via Enhanced CalibrationFindings2 citations
1844. Making Pre-trained Language Models Better Learn Few-Shot Spoken Language Understanding in More Practical ScenariosFindings2 citations
1845. Masked Audio Text Encoders are Effective Multi-Modal RescorersFindings2 citations
1846. Measuring the Instability of Fine-TuningLong2 citations
1847. Mind the Gap between the Application Track and the Real WorldShort2 citations
1848. Model Interpretability and Rationale Extraction by Input Mask OptimizationFindings2 citations
1849. Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text TransformersLong2 citations
1850. Modeling the Q-Diversity in a Min-max Play Game for Robust OptimizationFindings2 citations
1851. Multi-doc Hybrid Summarization via Salient Representation LearningIndustry2 citations
1852. Multijugate Dual Learning for Low-Resource Task-Oriented Dialogue SystemFindings2 citations
1853. NatCS: Eliciting Natural Customer Support DialoguesFindings2 citations
1854. On the Correspondence between Compositionality and Imitation in Emergent Neural CommunicationFindings2 citations
1855. On the Universal Adversarial Perturbations for Efficient Data-free Adversarial DetectionFindings2 citations
1856. On-the-fly Cross-lingual Masking for Multilingual Pre-trainingLong2 citations
1857. OpenPI-C: A Better Benchmark and Stronger Baseline for Open-Vocabulary State TrackingFindings2 citations
1858. PLAtE: A Large-scale Dataset for List Page Web ExtractionIndustry2 citations
1859. Peeking inside the black box: A Commonsense-aware Generative Framework for Explainable Complaint DetectionLong2 citations
1860. People and Places of Historical Europe: Bootstrapping Annotation Pipeline and a New Corpus of Named Entities in Late Medieval TextsFindings2 citations
1861. Probabilistic Transformer: A Probabilistic Dependency Model for Contextual Word RepresentationFindings2 citations
1862. Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading ComprehensionFindings2 citations
1863. RISE: Leveraging Retrieval Techniques for Summarization EvaluationFindings2 citations
1864. Reanalyzing L2 Preposition Learning with Bayesian Mixed Effects and a Pretrained Language ModelLong2 citations
1865. Reconstruction ProbingFindings2 citations
1866. Reducing cohort bias in natural language understanding systems with targeted self-training schemeIndustry2 citations
1867. Referring to Screen Texts with Voice AssistantsIndustry2 citations
1868. Regression-Free Model Updates for Spoken Language UnderstandingIndustry2 citations
1869. Risks and NLP Design: A Case Study on Procedural Document QAFindings2 citations
1870. Simple Augmentations of Logical Rules for Neuro-Symbolic Knowledge Graph CompletionShort2 citations
1871. SlowBERT: Slow-down Attacks on Input-adaptive Multi-exit BERTFindings2 citations
1872. Soft Alignment Objectives for Robust Adaptation of Language GenerationLong2 citations
1873. Solving Cosine Similarity Underestimation between High Frequency Words by ℓ2 Norm DiscountingFindings2 citations
1874. SongRewriter: A Chinese Song Rewriting System with Controllable Content and Rhyme SchemeFindings2 citations
1875. Spontaneous gestures encoded by hand positions improve language models: An Information-Theoretic motivated studyFindings2 citations
1876. Stop Pre-Training: Adapt Visual-Language Models to Unseen LanguagesShort2 citations
1877. Structured Mean-Field Variational Inference for Higher-Order Span-Based Semantic Role LabelingFindings2 citations
1878. Table and Image Generation for Investigating Knowledge of Entities in Pre-trained Vision and Language ModelsShort2 citations
1879. Target-Based Offensive Language IdentificationShort2 citations
1880. Target-Oriented Relation Alignment for Cross-Lingual Stance DetectionFindings2 citations
1881. Task-adaptive Label Dependency Transfer for Few-shot Named Entity RecognitionFindings2 citations
1882. The KITMUS Test: Evaluating Knowledge Integration from Multiple SourcesLong2 citations
1883. Theory of Mind in Freely-Told Children’s Narratives: A Classification ApproachFindings2 citations
1884. Towards Open Environment Intent PredictionFindings2 citations
1885. Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed RepresentationsLong2 citations
1886. Towards Zero-Shot Multilingual Transfer for Code-Switched ResponsesLong2 citations
1887. Type Enhanced BERT for Correcting NER ErrorsFindings2 citations
1888. Understanding Demonstration-based Learning from a Causal PerspectiveShort2 citations
1889. Using Neural Machine Translation for Generating Diverse Challenging Exercises for Language LearnerLong2 citations
1890. Using contradictions improves question answering systemsShort2 citations
1891. Using counterfactual contrast to improve compositional generalization for multi-step quantitative reasoningLong2 citations
1892. Weakly Supervised Vision-and-Language Pre-training with Relative RepresentationsLong2 citations
1893. Yes, this Way! Learning to Ground Referring Expressions into Actions with Intra-episodic Feedback from Supportive TeachersFindings2 citations
1894. infoVerse: A Universal Framework for Dataset Characterization with Multidimensional Meta-informationLong2 citations
1895. lilGym: Natural Language Visual Reasoning with Reinforcement LearningLong2 citations
1896. A Comparative Analysis of the Effectiveness of Rare Tokens on Creative Expression using ramBERTFindings1 citations
1897. A Multi-task Learning Framework for Quality EstimationFindings1 citations
1898. ACTC: Active Threshold Calibration for Cold-Start Knowledge Graph CompletionShort1 citations
1899. Abstract then Play: A Skill-centric Reinforcement Learning Framework for Text-based GamesFindings1 citations
1900. Analyzing Text Representations by Measuring Task AlignmentShort1 citations
1901. Annotating Research Infrastructure in Scientific Papers: An NLP-driven ApproachIndustry1 citations
1902. Another Dead End for Morphological Tags? Perturbed Inputs and ParsingFindings1 citations
1903. Are Layout-Infused Language Models Robust to Layout Distribution Shifts? A Case Study with Scientific DocumentsFindings1 citations
1904. Attend, Select and Eliminate: Accelerating Multi-turn Response Selection with Dual-attention-based Content EliminationFindings1 citations
1905. Automated Digitization of Unstructured Medical PrescriptionsIndustry1 citations
1906. Automatic Identification of Code-Switching Functions in Speech TranscriptsFindings1 citations
1907. Bridging The Gap: Entailment Fused-T5 for Open-retrieval Conversational Machine Reading ComprehensionLong1 citations
1908. Building Accurate Low Latency ASR for Streaming Voice Search in E-commerceIndustry1 citations
1909. C-XNLI: Croatian Extension of XNLI DatasetFindings1 citations
1910. CUPID: Curriculum Learning Based Real-Time Prediction using DistillationIndustry1 citations
1911. CWSeg: An Efficient and General Approach to Chinese Word SegmentationIndustry1 citations
1912. Categorial grammar induction from raw dataFindings1 citations
1913. CoMix: Guide Transformers to Code-Mix using POS structure and PhoneticsFindings1 citations
1914. Comparative evaluation of boundary-relaxed annotation for Entity Linking performanceLong1 citations
1915. Conjunct Lengths in English, Dependency Length Minimization, and Dependency Structure of CoordinationLong1 citations
1916. Constrained Tuple Extraction with Interaction-Aware NetworkLong1 citations
1917. Convergence and Diversity in the Control HierarchyLong1 citations
1918. Cross-task Knowledge Transfer for Extremely Weakly Supervised Text ClassificationFindings1 citations
1919. DARE: Towards Robust Text Explanations in Biomedical and Healthcare ApplicationsLong1 citations
1920. DSPM-NLG: A Dual Supervised Pre-trained Model for Few-shot Natural Language Generation in Task-oriented Dialogue SystemFindings1 citations
1921. Decomposed scoring of CCG dependenciesShort1 citations
1922. Deep Active Learning for Morphophonological ProcessingShort1 citations
1923. Differentiable Instruction Optimization for Cross-Task GeneralizationFindings1 citations
1924. Distinguishing Address vs. Reference Mentions of Personal Names in TextFindings1 citations
1925. Domain-Agnostic Neural Architecture for Class Incremental Continual Learning in Document Processing PlatformIndustry1 citations
1926. Domain-specific Attention with Distributional Signatures for Multi-Domain End-to-end Task-Oriented DialogueFindings1 citations
1927. Domain-specific transformer models for query translationIndustry1 citations
1928. DopplerBAS: Binaural Audio Synthesis Addressing Doppler EffectFindings1 citations
1929. Dramatic Conversation DisentanglementFindings1 citations
1930. EEL: Efficiently Encoding Lattices for RerankingLong1 citations
1931. Early Discovery of Disappearing Entities in MicroblogsLong1 citations
1932. Entity Contrastive Learning in a Large-Scale Virtual Assistant SystemIndustry1 citations
1933. Evaluating Zero-Shot Event Structures: Recommendations for Automatic Content Extraction (ACE) AnnotationsShort1 citations
1934. EvolveMT: an Ensemble MT Engine Improving Itself with Usage OnlyIndustry1 citations
1935. Explanation Graph Generation via Generative Pre-training over Synthetic GraphsFindings1 citations
1936. Exploring Variation of Results from Different Experimental ConditionsFindings1 citations
1937. Extracting Shopping Interest-Related Product Types from the WebFindings1 citations
1938. Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source LearningLong1 citations
1939. Hybrid-Regressive Paradigm for Accurate and Speed-Robust Neural Machine TranslationFindings1 citations
1940. INTapt: Information-Theoretic Adversarial Prompt Tuning for Enhanced Non-Native Speech RecognitionFindings1 citations
1941. Imagination is All You Need! Curved Contrastive Learning for Abstract Sequence Modeling Utilized on Long Short-Term Dialogue PlanningFindings1 citations
1942. Improving Grammar-based Sequence-to-Sequence Modeling with Decomposition and ConstraintsShort1 citations
1943. Improving Knowledge Production Efficiency With Question Answering on ConversationIndustry1 citations
1944. Investigating Transformer-Guided Chaining for Interpretable Natural Logic ReasoningFindings1 citations
1945. Learning Neuro-Symbolic World Models with Conversational ProprioceptionShort1 citations
1946. Leveraging Explicit Procedural Instructions for Data-Efficient Action PredictionFindings1 citations
1947. Lexical Translation Inconsistency-Aware Document-Level Translation RepairFindings1 citations
1948. Listener Model for the PhotoBook Referential Game with CLIPScores as Implicit Reference ChainShort1 citations
1949. Logic-driven Indirect Supervision: An Application to Crisis CounselingLong1 citations
1950. Logical Transformers: Infusing Logical Structures into Pre-Trained Language ModelsFindings1 citations
1951. MTR: A Dataset Fusing Inductive, Deductive, and Defeasible ReasoningFindings1 citations
1952. Massively Multilingual Lexical Specialization of Multilingual TransformersLong1 citations
1953. Misleading Relation Classifiers by Substituting Words in TextsFindings1 citations
1954. Mitigating the Learning Bias towards Repetition by Self-Contrastive Training for Open-Ended GenerationFindings1 citations
1955. MobileNMT: Enabling Translation in 15MB and 30msIndustry1 citations
1956. Model Analysis & Evaluation for Ambiguous Question AnsweringFindings1 citations
1957. Model-Based Simulation for Optimising Smart ReplyLong1 citations
1958. Morphological Inflection with Phonological FeaturesShort1 citations
1959. Multi-Agent Language Learning: Symbolic MappingFindings1 citations
1960. Multi-armed bandits for resource efficient, online optimization of language model pre-training: the use case of dynamic maskingFindings1 citations
1961. My side, your side and the evidence: Discovering aligned actor groups and the narratives they weaveLong1 citations
1962. Neural Networks Against (and For) Self-Training: Classification with Small Labeled and Large Unlabeled SetsFindings1 citations
1963. On the Evaluation of Neural Selective Prediction Methods for Natural Language ProcessingLong1 citations
1964. PEER: Pre-training ELECTRA Extended by RankingFindings1 citations
1965. PairSpanBERT: An Enhanced Language Model for Bridging ResolutionLong1 citations
1966. Pre-training Language Model as a Multi-perspective Course LearnerFindings1 citations
1967. Predicting Human Translation Difficulty Using Automatic Word AlignmentFindings1 citations
1968. Predicting Numerals in Text Using Nearest Neighbor Language ModelsFindings1 citations
1969. PruMUX: Augmenting Data Multiplexing with Model CompressionFindings1 citations
1970. Quantifying Train-Evaluation Overlap with Nearest NeighborsFindings1 citations
1971. READIN: A Chinese Multi-Task Benchmark with Realistic and Diverse Input NoisesLong1 citations
1972. Re-appraising the Schema Linking for Text-to-SQLFindings1 citations
1973. Revisiting Pathologies of Neural Models under Input ReductionFindings1 citations
1974. Robust Learning for Multi-party Addressee Recognition with Discrete Addressee CodebookShort1 citations
1975. Robustness of Multi-Source MT to Transcription ErrorsFindings1 citations
1976. SORTIE: Dependency-Aware Symbolic Reasoning for Logical Data-to-text GenerationFindings1 citations
1977. Stochastic Bridges as Effective Regularizers for Parameter-Efficient TuningFindings1 citations
1978. Syntax and Geometry of InformationLong1 citations
1979. TeCS: A Dataset and Benchmark for Tense Consistency of Machine TranslationShort1 citations
1980. The Mechanical Bard: An Interpretable Machine Learning Approach to Shakespearean Sonnet GenerationShort1 citations
1981. Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect EnhancementShort1 citations
1982. Two Examples are Better than One: Context Regularization for Gradient-based Prompt TuningFindings1 citations
1983. Typology Guided Multilingual Position Representations: Case on Dependency ParsingFindings1 citations
1984. UniFine: A Unified and Fine-grained Approach for Zero-shot Vision-Language UnderstandingFindings1 citations
1985. Unsupervised Open-domain Keyphrase GenerationLong1 citations
1986. Unsupervised Paraphrasing of Multiword ExpressionsFindings1 citations
1987. VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of TransformationsFindings1 citations
1988. Weakly supervised hierarchical multi-task classification of customer questionsIndustry1 citations
1989. When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer VariantsShort1 citations
1990. mOKB6: A Multilingual Open Knowledge Base Completion BenchmarkShort1 citations
1991. A Robust Information-Masking Approach for Domain Counterfactual GenerationFindings
1992. A Semi-Autoregressive Graph Generative Model for Dependency Graph ParsingFindings
1993. A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship AttributionFindings
1994. AMR-based Network for Aspect-based Sentiment AnalysisLong
1995. Adversarial Knowledge Stimulated Contrastive Prompting for Few-shot Language LearnersFindings
1996. Adversarial Textual Robustness on Visual DialogFindings
1997. An Empirical Analysis of Leveraging Knowledge for Low-Resource Task-Oriented Semantic ParsingFindings
1998. An Inclusive Notion of TextLong
1999. An Investigation of Noise in Morphological InflectionFindings
2000. An efficient method for Natural Language Querying on Structured DataIndustry

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