Elamur Research⌕
☰
home / venues / EMNLP / 2021 / papers

EMNLP 2021: all accepted papers

895 papers · page 1 of 9 · the most cited first · ← EMNLP 2021

1 2 … 9

  1. The Power of Scale for Parameter-Efficient Prompt TuningBrian Lester, Rami Al-Rfou, Noah Constant2,915 citations
  2. SimCSE: Simple Contrastive Learning of Sentence EmbeddingsTianyu Gao, Xingcheng Yao, Danqi Chen2,686 citations · our summary
  3. CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and GenerationYue Wang, Weishi Wang, Shafiq Joty et al.1,423 citations
  4. CLIPScore: A Reference-free Evaluation Metric for Image CaptioningJack Hessel, Ari Holtzman, Maxwell Forbes et al.1,191 citations · our summary
  5. Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment AnalysisWei Han, Hui Chen, Soujanya Poria515 citations · our summary
  6. VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text UnderstandingHu Xu, Gargi Ghosh, Po-Yao Huang et al.450 citations
  7. Transformer Feed-Forward Layers Are Key-Value MemoriesMor Geva, Roei Schuster, Jonathan Berant et al.328 citations
  8. Datasets: A Community Library for Natural Language ProcessingQuentin Lhoest, Albert Villanova del Moral, Yacine Jernite et al. · System Demonstrations327 citations
  9. PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language ModelsTorsten Scholak, Nathan Schucher, Dzmitry Bahdanau323 citations
  10. Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled CorpusJesse Dodge, Maarten Sap, Ana Marasović et al.289 citations
  11. FinQA: A Dataset of Numerical Reasoning over Financial DataZhiyu Chen, Wenhu Chen, Charese Smiley et al.241 citations · our summary
  12. Aspect Sentiment Quad Prediction as Paraphrase GenerationWenxuan Zhang, Yang Deng, Xin Li et al.212 citations · our summary
  13. Latent Hatred: A Benchmark for Understanding Implicit Hate SpeechMai ElSherief, Caleb Ziems, David Muchlinski et al.190 citations · our summary
  14. ONION: A Simple and Effective Defense Against Textual Backdoor AttacksFanchao Qi, Yangyi Chen, Mukai Li et al.189 citations · our summary
  15. TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph ForecastingHaohai Sun, Jialun Zhong, Yunpu Ma et al.187 citations
  16. AdapterDrop: On the Efficiency of Adapters in TransformersAndreas Rücklé, Gregor Geigle, Max Glockner et al.181 citations · our summary
  17. Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for LittleKoustuv Sinha, Robin Jia, Dieuwke Hupkes et al.181 citations · our summary
  18. Editing Factual Knowledge in Language ModelsNicola De Cao, Wilker Aziz, Ivan Titov176 citations
  19. Muppet: Massive Multi-task Representations with Pre-FinetuningArmen Aghajanyan, Anchit Gupta, Akshat Shrivastava et al.175 citations · our summary
  20. Fast WordPiece TokenizationXinying Song, Alex Salcianu, Yang Song et al.172 citations
  21. QuestEval: Summarization Asks for Fact-based EvaluationThomas Scialom, Paul-Alexis Dray, Sylvain Lamprier et al.169 citations · our summary
  22. Condenser: a Pre-training Architecture for Dense RetrievalLuyu Gao, Jamie Callan161 citations · our summary
  23. Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine TranslationMozhdeh Gheini, Xiang Ren, Jonathan May151 citations
  24. RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingRuiyang Ren, Yingqi Qu, Jing Liu et al.149 citations · our summary
  25. A Partition Filter Network for Joint Entity and Relation ExtractionZhiheng Yan, Chong Zhang, Jinlan Fu et al.142 citations
  26. Joint Multi-modal Aspect-Sentiment Analysis with Auxiliary Cross-modal Relation DetectionXincheng Ju, Dong Zhang, Rong Xiao et al.142 citations
  27. N-LTP: An Open-source Neural Language Technology Platform for ChineseWanxiang Che, Yunlong Feng, Libo Qin et al. · System Demonstrations135 citations
  28. Active Learning by Acquiring Contrastive ExamplesKaterina Margatina, Giorgos Vernikos, Loïc Barrault et al.134 citations
  29. Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuningRunxin Xu, Fuli Luo, Zhiyuan Zhang et al.133 citations · our summary
  30. CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive SummarizationShuyang Cao, Lu Wang132 citations · our summary
  31. Constrained Language Models Yield Few-Shot Semantic ParsersRichard Shin, Christopher Lin, Sam Thomson et al.132 citations
  32. Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style TransferFanchao Qi, Yangyi Chen, Xurui Zhang et al.127 citations · our summary
  33. Learning Neural Ordinary Equations for Forecasting Future Links on Temporal Knowledge GraphsZhen Han, Zifeng Ding, Yunpu Ma et al.125 citations
  34. Block Pruning For Faster TransformersFrançois Lagunas, Ella Charlaix, Victor Sanh et al.123 citations · our summary
  35. Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language TechnologiesSunipa Dev, Masoud Monajatipoor, Anaelia Ovalle et al.123 citations · our summary
  36. Surface Form Competition: Why the Highest Probability Answer Isn't Always RightAri Holtzman, Peter West, Vered Shwartz et al.120 citations · our summary
  37. Generating Datasets with Pretrained Language ModelsTimo Schick, Hinrich Schütze119 citations · our summary
  38. Contrastive Code Representation LearningParas Jain, Ajay Jain, Tianjun Zhang et al.118 citations
  39. The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer EncodersHan He, Jinho D. Choi116 citations
  40. Case-based Reasoning for Natural Language Queries over Knowledge BasesRajarshi Das, Manzil Zaheer, Dung Thai et al.115 citations
  41. HittER: Hierarchical Transformers for Knowledge Graph EmbeddingsSanxing Chen, Xiaodong Liu, Jianfeng Gao et al.115 citations
  42. XTREME-R: Towards More Challenging and Nuanced Multilingual EvaluationSebastian Ruder, Noah Constant, Jan Botha et al.115 citations · our summary
  43. $Q^2$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question AnsweringOr Honovich, Leshem Choshen, Roee Aharoni et al.112 citations · our summary
  44. Improving and Simplifying Pattern Exploiting TrainingDerek Tam, Rakesh R. Menon, Mohit Bansal et al.111 citations · our summary
  45. Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-TrainingZhengyan Li, Yicheng Zou, Chong Zhang et al.109 citations
  46. TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation GraphJiaxin Shi, Shulin Cao, Lei Hou et al.107 citations
  47. Gradient-based Adversarial Attacks against Text TransformersChuan Guo, Alexandre Sablayrolles, Hervé Jégou et al.106 citations · our summary
  48. Measuring Association Between Labels and Free-Text RationalesSarah Wiegreffe, Ana Marasović, Noah A. Smith105 citations · our summary
  49. CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLPQinyuan Ye, Bill Yuchen Lin, Xiang Ren103 citations
  50. Few-Shot Text Generation with Natural Language InstructionsTimo Schick, Hinrich Schütze103 citations · our summary
  51. Few-Shot Named Entity Recognition: An Empirical Baseline StudyJiaxin Huang, Chunyuan Li, Krishan Subudhi et al.101 citations
  52. Label Verbalization and Entailment for Effective Zero and Few-Shot Relation ExtractionOscar Sainz, Oier Lopez de Lacalle, Gorka Labaka et al.100 citations · our summary
  53. Backdoor Attacks on Pre-trained Models by Layerwise Weight PoisoningLinyang Li, Demin Song, Xiaonan Li et al.98 citations
  54. Entity-Based Knowledge Conflicts in Question AnsweringShayne Longpre, Kartik Perisetla, Anthony Chen et al.98 citations · our summary
  55. IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language GenerationSamuel Cahyawijaya, Genta Indra Winata, Bryan Wilie et al.98 citations
  56. IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary InitializationFajri Koto, Jey Han Lau, Timothy Baldwin97 citations
  57. BERT4GCN: Using BERT Intermediate Layers to Augment GCN for Aspect-based Sentiment ClassificationZeguan Xiao, Jiarun Wu, Qingliang Chen et al.94 citations
  58. Word-Level Coreference ResolutionVladimir Dobrovolskii92 citations · our summary
  59. Visually Grounded Reasoning across Languages and CulturesFangyu Liu, Emanuele Bugliarello, Edoardo Maria Ponti et al.91 citations
  60. Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their ConsequencesDenis Emelin, Ronan Le Bras, Jena D. Hwang et al.89 citations
  61. Balancing Methods for Multi-label Text Classification with Long-Tailed Class DistributionYi Huang, Buse Giledereli, Abdullatif Köksal et al.87 citations
  62. Dialogue State Tracking with a Language Model using Schema-Driven PromptingChia-Hsuan Lee, Hao Cheng, Mari Ostendorf85 citations
  63. Explaining Answers with Entailment TreesBhavana Dalvi, Peter Jansen, Oyvind Tafjord et al.85 citations · our summary
  64. Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence EncodersFangyu Liu, Ivan Vulić, Anna Korhonen et al.84 citations · our summary
  65. MultiEURLEX - A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transferIlias Chalkidis, Manos Fergadiotis, Ion Androutsopoulos84 citations · our summary
  66. MS\textasciicircum2: Multi-Document Summarization of Medical StudiesJay DeYoung, Iz Beltagy, Madeleine van Zuylen et al.83 citations
  67. Text2Mol: Cross-Modal Molecule Retrieval with Natural Language QueriesCarl Edwards, ChengXiang Zhai, Heng Ji83 citations · our summary
  68. Contrastive Explanations for Model InterpretabilityAlon Jacovi, Swabha Swayamdipta, Shauli Ravfogel et al.81 citations
  69. Simple Entity-Centric Questions Challenge Dense RetrieversChristopher Sciavolino, Zexuan Zhong, Jinhyuk Lee et al.81 citations · our summary
  70. Understanding and Overcoming the Challenges of Efficient Transformer QuantizationYelysei Bondarenko, Markus Nagel, Tijmen Blankevoort81 citations
  71. Exploring Underexplored Limitations of Cross-Domain Text-to-SQL GeneralizationYujian Gan, Xinyun Chen, Matthew Purver77 citations · our summary
  72. Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path GroundingNouha Dziri, Andrea Madotto, Osmar Zaïane et al.77 citations · our summary
  73. Do Transformer Modifications Transfer Across Implementations and Applications?Sharan Narang, Hyung Won Chung, Yi Tay et al.76 citations
  74. How to Train BERT with an Academic BudgetPeter Izsak, Moshe Berchansky, Omer Levy76 citations
  75. Narrative Theory for Computational Narrative UnderstandingAndrew Piper, Richard Jean So, David Bamman76 citations
  76. Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text ClassificationVarsha Suresh, Desmond C. Ong75 citations
  77. Visual News: Benchmark and Challenges in News Image CaptioningFuxiao Liu, Yinghan Wang, Tianlu Wang et al.75 citations
  78. A Novel Global Feature-Oriented Relational Triple Extraction Model based on Table FillingFeiliang Ren, Longhui Zhang, Shujuan Yin et al.74 citations
  79. Exploring Task Difficulty for Few-Shot Relation ExtractionJiale Han, Bo Cheng, Wei Lu73 citations
  80. Competency Problems: On Finding and Removing Artifacts in Language DataMatt Gardner, William Merrill, Jesse Dodge et al.72 citations
  81. Continual Learning in Task-Oriented Dialogue SystemsAndrea Madotto, Zhaojiang Lin, Zhenpeng Zhou et al.72 citations
  82. What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained TransformersBoseop Kim, HyoungSeok Kim, Sang-Woo Lee et al.72 citations
  83. NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal MediaGrace Luo, Trevor Darrell, Anna Rohrbach71 citations
  84. UNKs Everywhere: Adapting Multilingual Language Models to New ScriptsJonas Pfeiffer, Ivan Vulić, Iryna Gurevych et al.71 citations · our summary
  85. Few-Shot Intent Detection via Contrastive Pre-Training and Fine-TuningJianguo Zhang, Trung Bui, Seunghyun Yoon et al.70 citations
  86. What to Pre-Train on? Efficient Intermediate Task SelectionClifton Poth, Jonas Pfeiffer, Andreas Rücklé et al.70 citations · our summary
  87. Contrastive Out-of-Distribution Detection for Pretrained TransformersWenxuan Zhou, Fangyu Liu, Muhao Chen69 citations
  88. Deep Attention Diffusion Graph Neural Networks for Text ClassificationYonghao Liu, Renchu Guan, Fausto Giunchiglia et al.69 citations
  89. Evaluating the Robustness of Neural Language Models to Input PerturbationsMilad Moradi, Matthias Samwald69 citations
  90. Improving Question Answering Model Robustness with Synthetic Adversarial Data GenerationMax Bartolo, Tristan Thrush, Robin Jia et al.69 citations
  91. ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual CorporaXuan Ouyang, Shuohuan Wang, Chao Pang et al.68 citations · our summary
  92. Building and Evaluating Open-Domain Dialogue Corpora with Clarifying QuestionsMohammad Aliannejadi, Julia Kiseleva, Aleksandr Chuklin et al.67 citations
  93. LayoutReader: Pre-training of Text and Layout for Reading Order DetectionZilong Wang, Yiheng Xu, Lei Cui et al.67 citations
  94. MATE: Multi-view Attention for Table Transformer EfficiencyJulian Eisenschlos, Maharshi Gor, Thomas Müller et al.67 citations
  95. Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive SummarizationTiezheng Yu, Wenliang Dai, Zihan Liu et al.67 citations
  96. Can Language Models be Biomedical Knowledge Bases?Mujeen Sung, Jinhyuk Lee, Sean Yi et al.66 citations · our summary
  97. Solving Aspect Category Sentiment Analysis as a Text Generation TaskJian Liu, Zhiyang Teng, Leyang Cui et al.66 citations
  98. All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational QualityWilliam Timkey, Marten van Schijndel65 citations · our summary
  99. RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP ModelsWenkai Yang, Yankai Lin, Peng Li et al.65 citations · our summary
  100. Efficient Nearest Neighbor Language ModelsJunxian He, Graham Neubig, Taylor Berg-Kirkpatrick64 citations · our summary

1 2 … 9

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/venues/emnlp/2021/papers/