172篇 | COLING 2022论文集

1. Mintaka：A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering

2. Hypothesis Engineering for Zero-Shot Hate Speech Detection

3. The Effectiveness of Masked Language Modeling and Adapters for Factual Knowledge Injection

4. Medical Question Understanding and Answering with Knowledge Grounding and Semantic Self-Supervision

5. Generate-and-Retrieve：use your predictions to improve retrieval for semantic parsing

6. Perturbations and Subpopulations for Testing Robustness in Token-Based Argument Unit Recognition

7. A Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection

8. COLO：A Contrastive Learning based Re-ranking Framework for One-Stage Summarization

9. RuDSI：graph-based word sense induction dataset for Russian

10. Evaluating Agent Interactions Through Episodic Knowledge Graphs

11. Conversational QA Dataset Generation with Answer Revision

12. An Information Minimization Based Contrastive Learning Model for Unsupervised Sentence Embeddings Learning

13. Equivariant Transduction through Invariant Alignment

14. Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model

15. Subject Verb Agreement Error Patterns in Meaningless Sentences：Humans vs. BERT

16. Bias at a Second Glance：A Deep Dive into Bias for German Educational Peer-Review Data Modeling

17. Is More Data Better？Re-thinking the Importance of Efficiency in Abusive Language Detection with Transformers-Based Active Learning

18. LINGUIST：Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Tagging

19. Twitter Topic Classification

20. Target-Guided Open-Domain Conversation Planning

21. A Simple Temporal Information Matching Mechanism for Entity Alignment Between Temporal Knowledge Graphs

22. Incorporating Casual Analysis into Diversified and Logical Response Generation

23. CofeNet：Context and Former-Label Enhanced Net for Complicated Quotation Extraction

24. Automatic Label Sequence Generation for Prompting Sequence-to-sequence Models

25. The first neural machine translation system for the Erzya language

26. Scene Graph Modification as Incremental Structure Expanding

27. Learning Decoupled Retrieval Representation for Nearest Neighbour Neural Machine Translation

28. Joint Language Semantic and Structure Embedding for Knowledge Graph Completion

29. Autoregressive Entity Generation for End-to-End Task-Oriented Dialog

30. LED down the rabbit hole：exploring the potential of global attention for biomedical multi-document summarisation

31. Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection

32. Improving Topic Segmentation by Injecting Discourse Dependencies

33. Overcoming Language Priors in Visual Question Answering via Distinguishing Superficially Similar Instances

34. Detecting Generated Scientific Papers using an Ensemble of Transformer Models

35. Unsupervised Lexical Substitution with Decontextualised Embeddings

36. APPDIA：A Discourse-aware Transformer-based Style Transfer Model for Offensive Social Media Conversations

37. Selective Token Generation for Few-shot Natural Language Generation

38. Belief Revision based Caption Re-ranker with Visual Semantic Information

39. A Multi-turn Machine Reading Comprehension Framework with Rethink Mechanism for Emotion-Cause Pair Extraction

40. Less is Better：Recovering Intended-Feature Subspace to Robustify NLU Models

41. Adaptive Natural Language Generation for Task-oriented Dialogue via Reinforcement Learning

42. Possible Stories：Evaluating Situated Commonsense Reasoning under Multiple Possible Scenarios

43. PINEAPPLE：Personifying INanimate Entities by Acquiring Parallel Personification data for Learning Enhanced generation

44. ConFiguRe：Exploring Discourse-level Chinese Figures of Speech

45. Corpus-Guided Contrast Sets for Morphosyntactic Feature Detection in Low-Resource English Varieties

46. Machine Reading, Fast and Slow：When Do Models UnderstandLanguage？

47. Measuring Geographic Performance Disparities of Offensive Language Classifiers

48. Knowledge Is Flat：A Seq2Seq Generative Framework for Various Knowledge Graph Completion

49. TempoWiC：An Evaluation Benchmark for Detecting Meaning Shift in Social Media

50. CommunityLM：Probing Partisan Worldviews from Language Models

51. Prompt-based Conservation Learning for Multi-hop Question Answering

52. Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across Corpora

53. The Fragility of Multi-Treebank Parsing Evaluation

54. CoHS-CQG：Context and History Selection for Conversational Question Generation

55. WildQA：In-the-Wild Video Question Answering

56. SPACE-2：Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding

57. Few Clean Instances Help Denoising Distant Supervision

58. COMMA：Modeling Relationship among Motivations, Emotions and Actions in Language-based Human Activities

59. Prompt Combines Paraphrase：Teaching Pre-trained Models to Understand Rare Biomedical Words

60. SUN：Exploring Intrinsic Uncertainties in Text-to-SQL Parsers

61. ImageArg：A Multi-modal Tweet Dataset for Image Persuasiveness Mining

62. Classical Sequence Match is a Competitive Few-Shot One-Class Learner

63. Don't Judge a Language Model by Its Last Layer：Contrastive Learning with Layer-Wise Attention Pooling

64. Visual Recipe Flow：A Dataset for Learning Visual State Changes of Objects with Recipe Flows

65. Ruleformer：Context-aware Differentiable Rule Mining over Knowledge Graph

66. Large-scale Evaluation of Transformer-based Article Encoders on the Task of Citation Recommendation

67. DoubleMix：Simple Interpolation-Based Data Augmentation for Text Classification

68. Open-Domain Dialog Evaluation using Follow-Ups Likelihood

69. Semantic-Preserving Adversarial Code Comprehension

70. SANCL：Multimodal Review Helpfulness Prediction with Selective Attention and Natural Contrastive Learning

71. CSL：A Large-scale Chinese Scientific Literature Dataset

72. Domain Adaptation for Question Answering via Question Classification

73. A Survey in Automatic Irony Processing：Linguistic, Cognitive, and Multi-X Perspectives

74. Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification

75. Harnessing Abstractive Summarization for Fact-Checked Claim Detection

76. Text Simplification of College Admissions Instructions：A Professionally Simplified and Verified Corpus

77. Multi-Document Scientific Summarization from a Knowledge Graph-Centric View

78. Enhancing Pre-trained Models with Text Structure Knowledge for Question Generation

79. Adapting to Non-Centered Languages for Zero-shot Multilingual Translation

80. Joint Alignment of Multi-Task Feature and Label Spaces for Emotion Cause Pair Extraction

81. SynSciPass：detecting appropriate uses of scientific text generation

82. CLaCLab at SocialDisNER：Using Medical Gazetteers for Named-Entity Recognition of Disease Mentions in Spanish Tweets

83. On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine Translation

84. Layer or Representation Space：What makes BERT-based Evaluation Metrics Robust？

85. Rare but Severe Neural Machine Translation Errors Induced by Minimal Deletion：An Empirical Study on Chinese and English

86. CONCRETE：Improving Cross-lingual Fact-checking with Cross-lingual Retrieval

87. Multi-Figurative Language Generation

88. Continuous Decomposition of Granularity for Neural Paraphrase Generation

89. SCL-RAI：Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER

90. Every picture tells a story：Image-grounded controllable stylistic story generation

91. Informative Language Representation Learning for Massively Multilingual Neural Machine Translation

92. Mind the Gap！Injecting Commonsense Knowledge for Abstractive Dialogue Summarization

93. Multi-modal Contrastive Representation Learning for Entity Alignment

94. Exploiting Hybrid Semantics of Relation Paths for Multi-hop Question Answering Over Knowledge Graphs

95. Structural Bias for Aspect Sentiment Triplet Extraction

96. Focus-Driven Contrastive Learniang for Medical Question Summarization

97. KoCHET：a Korean Cultural Heritage corpus for Entity-related Tasks

98. Find the Funding：Entity Linking with Incomplete Funding Knowledge Bases

99. Do language models make human-like predictions about the coreferents of Italian anaphoric zero pronouns？

100. MultiCoNER：A Large-scale Multilingual dataset for Complex Named Entity Recognition

101. IMCI：Integrate Multi-view Contextual Information for Fact Extraction and Verification

102. A Multi-Format Transfer Learning Model for Event Argument Extraction via Variational Information Bottleneck

103. Domain-Specific NER via Retrieving Correlated Samples

104. Coalescing Global and Local Information for Procedural Text Understanding

105. AiM：Taking Answers in Mind to Correct Chinese Cloze Tests in Educational Applications

106. GRASP：Guiding model with RelAtional Semantics using Prompt for Dialogue Relation Extraction

107. Of Human Criteria and Automatic Metrics：A Benchmark of the Evaluation of Story Generation

108. PSSAT：A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling

109. DPTDR：Deep Prompt Tuning for Dense Passage Retrieval

110. FactMix：Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition

111. A Hierarchical Interactive Network for Joint Span-based Aspect-Sentiment Analysis

112. Flat Multi-modal Interaction Transformer for Named Entity Recognition

113. Doc-GCN：Heterogeneous Graph Convolutional Networks for Document Layout Analysis

114. CLOWER：A Pre-trained Language Model with Contrastive Learning over Word and Character Representations

115. Unsupervised Question Answering via Answer Diversifying

116. Few-Shot Table-to-Text Generation with Prefix-Controlled Generator

117. K-MHaS：A Multi-label Hate Speech Detection Dataset in Korean Online News Comment

118. DP-Rewrite：Towards Reproducibility and Transparency in Differentially Private Text Rewriting

119. Neuro-Symbolic Visual Dialog

120. Locate Then Ask：Interpretable Stepwise Reasoning for Multi-hop Question Answering

121. Recent Advances in Text-to-SQL：A Survey of What We Have and What We Expect

122. MockingBERT：A Method for Retroactively Adding Resilience to NLP Models

123. Combining Compressions for Multiplicative Size Scaling on Natural Language Tasks

124. Using Multi-Encoder Fusion Strategies to Improve Personalized Response Selection

125. Coarse-to-Fine：Hierarchical Multi-task Learning for Natural Language Understanding

126. MulZDG：Multilingual Code-Switching Framework for Zero-shot Dialogue Generation

127. EmoMent：An Emotion Annotated Mental Health Corpus from two South Asian Countries

128. Summarizing Patients Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Models

129. Ask Question First for Enhancing Lifelong Language Learning

130. Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction

131. An Efficient Coarse-to-Fine Facet-Aware Unsupervised Summarization Framework based on Semantic Blocks

132. Understanding Attention for Vision-and-Language Tasks

133. Debiasing isn't enough！-- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks

134. Persian Natural Language Inference：A Meta-learning approach

135. Learn2Weight：Parameter Adaptation against Similar-domain Adversarial Attacks

136. Semantic Structure based Query Graph Prediction for Question Answering over Knowledge Graph

137. End-to-end Dense Video Captioning as Sequence Generation

138. A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment Analysis

139. Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning

140. MedDistant19：Towards an Accurate Benchmark for Broad-Coverage Biomedical Relation Extraction

141. PSP：Pre-trained Soft Prompts for Few-Shot Abstractive Summarization

142. Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval

143. Impact of Environmental Noise on Alzheimer's Disease Detection from Speech：Should You Let a Baby Cry？

144. Continuous Detection, Rapidly React：Unseen Rumors Detection based on Continual Prompt-Tuning

145. DialMed：A Dataset for Dialogue-based Medication Recommendation

146. CINO：A Chinese Minority Pre-trained Language Model

147. Decorrelate Irrelevant, Purify Relevant：Overcome Textual Spurious Correlations from a Feature Perspective

148. Pan More Gold from the Sand：Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation

149. Visual Information Guided Zero-Shot Paraphrase Generation

150. Context-Tuning：Learning Contextualized Prompts for Natural Language Generation

151. ArT：All-round Thinker for Unsupervised Commonsense Question-Answering

152. Improving Both Domain Robustness and Domain Adaptability in Machine Translation

153. Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing

154. Perform Like an Engine：A Closed-Loop Neural-Symbolic Learning Framework for Knowledge Graph Inference

155. Semantic Role Labeling as Dependency Parsing：Exploring Latent Tree Structures Inside Arguments

156. KNOT：Knowledge Distillation using Optimal Transport for Solving NLP Tasks

157. Hierarchical information matters：Text classification via tree based graph neural network

158. Can Edge Probing Tasks Reveal Linguistic Knowledge in QA Models？

159. An MRC Framework for Semantic Role Labeling

160. ESimCSE：Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding

161. Smoothed Contrastive Learning for Unsupervised Sentence Embedding

162. Paraphrase Generation as Unsupervised Machine Translation

163. LightNER：A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Prompting

164. Student Surpasses Teacher：Imitation Attack for Black-Box NLP APIs

165. Diversifying Neural Text Generation with Part-of-Speech Guided Softmax and Sampling

166. Effect of Post-processing on Contextualized Word Representations

167. A Survey on Multimodal Disinformation Detection

168. Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings

169. Summarize, Outline, and Elaborate：Long-Text Generation via Hierarchical Supervision from Extractive Summaries

170. Case-Based Abductive Natural Language Inference

171. Alleviating the Inequality of Attention Heads for Neural Machine Translation

172. Extracting a Knowledge Base of COVID-19 Events from Social Media