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

NAACL 2021: all accepted papers

560 papers · page 1 of 6 · the most cited first · ← NAACL 2021

1 2 … 6

  1. mT5: A Massively Multilingual Pre-trained Text-to-Text TransformerLinting Xue, Noah Constant, Adam Roberts et al.1,621 citations · our summary
  2. It's Not Just Size That Matters: Small Language Models Are Also Few-Shot LearnersTimo Schick, Hinrich Schütze · 🏆 Outstanding Long Paper685 citations · our summary
  3. Unified Pre-training for Program Understanding and GenerationWasi Ahmad, Saikat Chakraborty, Baishakhi Ray et al.608 citations · our summary
  4. QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question AnsweringMichihiro Yasunaga, Hongyu Ren, Antoine Bosselut et al.522 citations
  5. A Frustratingly Easy Approach for Entity and Relation ExtractionZexuan Zhong, Danqi Chen477 citations · our summary
  6. RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question AnsweringYingqi Qu, Yuchen Ding, Jing Liu et al.356 citations · our summary
  7. KILT: a Benchmark for Knowledge Intensive Language TasksFabio Petroni, Aleksandra Piktus, Angela Fan et al.339 citations · our summary
  8. Self-Alignment Pretraining for Biomedical Entity RepresentationsFangyu Liu, Ehsan Shareghi, Zaiqiao Meng et al.335 citations · our summary
  9. Learning How to Ask: Querying LMs with Mixtures of Soft PromptsGuanghui Qin, Jason Eisner · 🏆 Best Short Paper328 citations · our summary
  10. Are NLP Models really able to Solve Simple Math Word Problems?Arkil Patel, Satwik Bhattamishra, Navin Goyal290 citations · our summary
  11. A Survey on Recent Approaches for Natural Language Processing in Low-Resource ScenariosMichael A. Hedderich, Lukas Lange, Heike Adel et al.260 citations · our summary
  12. Factual Probing Is [MASK]: Learning vs. Learning to RecallZexuan Zhong, Dan Friedman, Danqi Chen260 citations · our summary
  13. Document-Level Event Argument Extraction by Conditional GenerationSha Li, Heng Ji, Jiawei Han254 citations · our summary
  14. InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-TrainingZewen Chi, Li Dong, Furu Wei et al.249 citations
  15. Dynabench: Rethinking Benchmarking in NLPDouwe Kiela, Max Bartolo, Yixin Nie et al.229 citations
  16. GSum: A General Framework for Guided Neural Abstractive SummarizationZi-Yi Dou, Pengfei Liu, Hiroaki Hayashi et al.200 citations · our summary
  17. Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality MetricsArtidoro Pagnoni, Vidhisha Balachandran, Yulia Tsvetkov190 citations · our summary
  18. Aspect-based Sentiment Analysis with Type-aware Graph Convolutional Networks and Layer EnsembleYuanhe Tian, Guimin Chen, Yan Song187 citations
  19. COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted ListLuyu Gao, Zhuyun Dai, Jamie Callan186 citations · our summary
  20. Supporting Clustering with Contrastive LearningDejiao Zhang, Feng Nan, Xiaokai Wei et al.185 citations · our summary
  21. How many data points is a prompt worth?Teven Le Scao, Alexander Rush · 🏆 Outstanding Short Paper179 citations · our summary
  22. Contextualized Perturbation for Textual Adversarial AttackDianqi Li, Yizhe Zhang, Hao Peng et al.178 citations · our summary
  23. Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring TasksNandan Thakur, Nils Reimers, Johannes Daxenberger et al.176 citations · our summary
  24. QMSum: A New Benchmark for Query-based Multi-domain Meeting SummarizationMing Zhong, Da Yin, Tao Yu et al.174 citations · our summary
  25. Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTaJunqi Dai, Hang Yan, Tianxiang Sun et al.163 citations
  26. Efficient Attentions for Long Document SummarizationLuyang Huang, Shuyang Cao, Nikolaus Parulian et al.143 citations · our summary
  27. Improving Factual Completeness and Consistency of Image-to-Text Radiology Report GenerationYasuhide Miura, Yuhao Zhang, Emily Tsai et al.138 citations
  28. Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-trainingOshin Agarwal, Heming Ge, Siamak Shakeri et al.136 citations · our summary
  29. A Dataset of Information-Seeking Questions and Answers Anchored in Research PapersPradeep Dasigi, Kyle Lo, Iz Beltagy et al.135 citations · our summary
  30. The Curious Case of Hallucinations in Neural Machine TranslationVikas Raunak, Arul Menezes, Marcin Junczys-Dowmunt128 citations · our summary
  31. UmlsBERT: Clinical Domain Knowledge Augmentation of Contextual Embeddings Using the Unified Medical Language System MetathesaurusGeorge Michalopoulos, Yuanxin Wang, Hussam Kaka et al.125 citations
  32. Open-Domain Question Answering Goes Conversational via Question RewritingRaviteja Anantha, Svitlana Vakulenko, Zhucheng Tu et al.123 citations · our summary
  33. TABBIE: Pretrained Representations of Tabular DataHiroshi Iida, Dung Thai, Varun Manjunatha et al.123 citations · our summary
  34. The Importance of Modeling Social Factors of Language: Theory and PracticeDirk Hovy, Diyi Yang122 citations · our summary
  35. COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report GenerationQingyun Wang, Manling Li, Xuan Wang et al. · Demonstrations · 🏆 Best Demo Paper121 citations
  36. Enhancing Factual Consistency of Abstractive SummarizationChenguang Zhu, William Hinthorn, Ruochen Xu et al.121 citations · our summary
  37. Get Your Vitamin C! Robust Fact Verification with Contrastive EvidenceTal Schuster, Adam Fisch, Regina Barzilay120 citations · our summary
  38. XOR QA: Cross-lingual Open-Retrieval Question AnsweringAkari Asai, Jungo Kasai, Jonathan Clark et al.110 citations · our summary
  39. Hurdles to Progress in Long-form Question AnsweringKalpesh Krishna, Aurko Roy, Mohit Iyyer109 citations · our summary
  40. Concealed Data Poisoning Attacks on NLP ModelsEric Wallace, Tony Zhao, Shi Feng et al.108 citations
  41. Self-training Improves Pre-training for Natural Language UnderstandingJingfei Du, Edouard Grave, Beliz Gunel et al.106 citations · our summary
  42. Temporal Knowledge Graph Completion using a Linear Temporal Regularizer and Multivector EmbeddingsChengjin Xu, Yung-Yu Chen, Mojtaba Nayyeri et al.104 citations
  43. Annotating and Modeling Fine-grained Factuality in SummarizationTanya Goyal, Greg Durrett99 citations · our summary
  44. Robustness Gym: Unifying the NLP Evaluation LandscapeKaran Goel, Nazneen Fatema Rajani, Jesse Vig et al. · Demonstrations98 citations
  45. What Will it Take to Fix Benchmarking in Natural Language Understanding?Samuel R. Bowman, George Dahl95 citations
  46. Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?Eric Lehman, Sarthak Jain, Karl Pichotta et al.93 citations
  47. MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language SequencesJianing Yang, Yongxin Wang, Ruitao Yi et al.93 citations
  48. Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training ApproachYue Yu, Simiao Zuo, Haoming Jiang et al.92 citations
  49. HONEST: Measuring Hurtful Sentence Completion in Language ModelsDebora Nozza, Federico Bianchi, Dirk Hovy91 citations · our summary
  50. ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation LearningChih-Yao Chen, Cheng-Te Li91 citations · our summary
  51. MediaSum: A Large-scale Media Interview Dataset for Dialogue SummarizationChenguang Zhu, Yang Liu, Jie Mei et al.90 citations · our summary
  52. SmBoP: Semi-autoregressive Bottom-up Semantic ParsingOhad Rubin, Jonathan Berant90 citations
  53. Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP ModelsWenkai Yang, Lei Li, Zhiyuan Zhang et al.88 citations · our summary
  54. LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text RetrievalSiqi Sun, Yen-Chun Chen, Linjie Li et al.87 citations
  55. Structure-Grounded Pretraining for Text-to-SQLXiang Deng, Ahmed Hassan Awadallah, Christopher Meek et al.86 citations · our summary
  56. Multimodal End-to-End Sparse Model for Emotion RecognitionWenliang Dai, Samuel Cahyawijaya, Zihan Liu et al.84 citations
  57. Adversarial Learning for Zero-Shot Stance Detection on Social MediaEmily Allaway, Malavika Srikanth, Kathleen McKeown83 citations · our summary
  58. Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and SelectionSihao Chen, Fan Zhang, Kazoo Sone et al.83 citations · our summary
  59. Knowledge Enhanced Masked Language Model for Stance DetectionKornraphop Kawintiranon, Lisa Singh82 citations · our summary
  60. DART: Open-Domain Structured Data Record to Text GenerationLinyong Nan, Dragomir Radev, Rui Zhang et al.81 citations
  61. Structure-Aware Abstractive Conversation Summarization via Discourse and Action GraphsJiaao Chen, Diyi Yang81 citations · our summary
  62. Introducing CAD: the Contextual Abuse DatasetBertie Vidgen, Dong Nguyen, Helen Margetts et al.80 citations · our summary
  63. Controllable Text Simplification with Explicit ParaphrasingMounica Maddela, Fernando Alva-Manchego, Wei Xu78 citations · our summary
  64. Open Domain Question Answering over Tables via Dense RetrievalJonathan Herzig, Thomas Müller, Syrine Krichene et al.78 citations · our summary
  65. Paragraph-level Simplification of Medical TextsAshwin Devaraj, Iain Marshall, Byron Wallace et al.76 citations · our summary
  66. Representing Numbers in NLP: a Survey and a VisionAvijit Thawani, Jay Pujara, Filip Ilievski et al.75 citations
  67. Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights CasesIlias Chalkidis, Manos Fergadiotis, Dimitrios Tsarapatsanis et al.74 citations · our summary
  68. MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification TheoriesMinjin Choi, Sunkyung Lee, Eunseong Choi et al.72 citations
  69. Abstract Meaning Representation Guided Graph Encoding and Decoding for Joint Information ExtractionZixuan Zhang, Heng Ji71 citations
  70. Graph Convolutional Networks for Event Causality Identification with Rich Document-level StructuresMinh Tran Phu, Thien Huu Nguyen71 citations
  71. Towards Few-shot Fact-Checking via PerplexityNayeon Lee, Yejin Bang, Andrea Madotto et al.71 citations
  72. Continual Learning for Text Classification with Information Disentanglement Based RegularizationYufan Huang, Yanzhe Zhang, Jiaao Chen et al.70 citations
  73. ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating PredictionJiahao Bu, Lei Ren, Shuang Zheng et al.68 citations
  74. GEMNET: Effective Gated Gazetteer Representations for Recognizing Complex Entities in Low-context InputTao Meng, Anjie Fang, Oleg Rokhlenko et al.68 citations
  75. HTCInfoMax: A Global Model for Hierarchical Text Classification via Information MaximizationZhongfen Deng, Hao Peng, Dongxiao He et al.68 citations
  76. Industry Scale Semi-Supervised Learning for Natural Language UnderstandingLuoxin Chen, Francisco Garcia, Varun Kumar et al. · Industry Papers68 citations
  77. Meta-Learning for Domain Generalization in Semantic ParsingBailin Wang, Mirella Lapata, Ivan Titov68 citations
  78. AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive SummarizationTiezheng Yu, Zihan Liu, Pascale Fung67 citations
  79. Beyond Black & White: Leveraging Annotator Disagreement via Soft-Label Multi-Task LearningTommaso Fornaciari, Alexandra Uma, Silviu Paun et al.65 citations · our summary
  80. Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data AugmentationAlexander Fabbri, Simeng Han, Haoyuan Li et al.65 citations
  81. ESC: Redesigning WSD with Extractive Sense ComprehensionEdoardo Barba, Tommaso Pasini, Roberto Navigli64 citations
  82. Progressive Generation of Long Text with Pretrained Language ModelsBowen Tan, Zichao Yang, Maruan Al-Shedivat et al.64 citations
  83. Self-Training with Weak SupervisionGiannis Karamanolakis, Subhabrata Mukherjee, Guoqing Zheng et al.64 citations
  84. Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU modelsMengnan Du, Varun Manjunatha, Rajiv Jain et al.64 citations
  85. Beyond Fair Pay: Ethical Implications of NLP CrowdsourcingBoaz Shmueli, Jan Fell, Soumya Ray et al.63 citations
  86. Bot-Adversarial Dialogue for Safe Conversational AgentsJing Xu, Da Ju, Margaret Li et al.63 citations · our summary
  87. X-Class: Text Classification with Extremely Weak SupervisionZihan Wang, Dheeraj Mekala, Jingbo Shang61 citations
  88. NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic ConstraintsXiming Lu, Peter West, Rowan Zellers et al.60 citations · our summary
  89. Detoxifying Language Models Risks Marginalizing Minority VoicesAlbert Xu, Eshaan Pathak, Eric Wallace et al.58 citations · our summary
  90. Pretrained Transformers for Text Ranking: BERT and BeyondAndrew Yates, Rodrigo Nogueira, Jimmy Lin · Tutorials58 citations
  91. Emotion Classification in a Resource Constrained Language Using Transformer-based ApproachAvishek Das, Omar Sharif, Mohammed Moshiul Hoque et al. · Student Research Workshop57 citations
  92. Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue StateTrackingZhaojiang Lin, Bing Liu, Seungwhan Moon et al.57 citations
  93. Mask Attention Networks: Rethinking and Strengthen TransformerZhihao Fan, Yeyun Gong, Dayiheng Liu et al.57 citations
  94. Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!Xuanli He, Lingjuan Lyu, Qiongkai Xu et al.57 citations
  95. Topic Model or Topic Twaddle? Re-evaluating Semantic Interpretability MeasuresCaitlin Doogan, Wray Buntine57 citations
  96. TaxoClass: Hierarchical Multi-Label Text Classification Using Only Class NamesJiaming Shen, Wenda Qiu, Yu Meng et al.56 citations
  97. Cross-Task Instance Representation Interactions and Label Dependencies for Joint Information Extraction with Graph Convolutional NetworksMinh Van Nguyen, Viet Dac Lai, Thien Huu Nguyen55 citations
  98. Grey-box Adversarial Attack And Defence For Sentiment ClassificationYing Xu, Xu Zhong, Antonio Jimeno Yepes et al.54 citations
  99. Efficiently Summarizing Text and Graph Encodings of Multi-Document ClustersRamakanth Pasunuru, Mengwen Liu, Mohit Bansal et al.53 citations
  100. Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language ModelsPo-Yao Huang, Mandela Patrick, Junjie Hu et al.53 citations

1 2 … 6

↑ back to top

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