📰 ACL 2021 — accepted papers

ACL 2021 is the 2021 edition of the Annual Meeting of the Association for Computational Linguistics (ACL), held in Online, August 2021 (publisher: Association for Computational Linguistics). The ACL Anthology lists 795 papers of it in 5 tracks; our library holds 89 with our summaries. Below: its awards, the most cited papers, every accepted paper, and ours with their topics, authors and institutions.

Tracks

Long Papers571Short Papers139System Demonstrations43Student Research Workshop36Tutorial Abstracts6

Awards

As the ACL Anthology records them.

1. Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-TuningArmen Aghajanyan, Sonal Gupta, Luke Zettlemoyer · Long Papers · 🏆 Outstanding Paper335 citations · our summary
2. All That's `Human' Is Not Gold: Evaluating Human Evaluation of Generated TextElizabeth Clark, Tal August, Sofia Serrano et al. · Long Papers · 🏆 Outstanding Paper275 citations
3. Including Signed Languages in Natural Language ProcessingKayo Yin, Amit Moryossef, Julie Hochgesang et al. · Long Papers · 🏆 Best Theme Paper75 citations · our summary
4. Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 PapersBenjamin Marie, Atsushi Fujita, Raphael Rubino · Long Papers · 🏆 Outstanding Paper72 citations
5. UnNatural Language InferenceKoustuv Sinha, Prasanna Parthasarathi, Joelle Pineau et al. · Long Papers · 🏆 Outstanding Paper71 citations · our summary
6. Vocabulary Learning via Optimal Transport for Neural Machine TranslationJingjing Xu, Hao Zhou, Chun Gan et al. · Long Papers · 🏆 Best Paper61 citations
7. Neural Machine Translation with Monolingual Translation MemoryDeng Cai, Yan Wang, Huayang Li et al. · Long Papers · 🏆 Outstanding Paper60 citations
8. Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question AnsweringSiddharth Karamcheti, Ranjay Krishna, Li Fei-Fei et al. · Long Papers · 🏆 Outstanding Paper49 citations
9. ExplainaBoard: An Explainable Leaderboard for NLPPengfei Liu, Jinlan Fu, Yang Xiao et al. · System Demonstrations · 🏆 Best Demonstration Paper34 citations
10. ESRA: Explainable Scientific Research AssistantPollawat Hongwimol, Peeranuth Kehasukcharoen, Pasit Laohawarutchai et al. · System Demonstrations · 🏆 Best Demonstration Runner-up1 citation

Most cited papers

By their OpenAlex citations; a paper with our summary links to its page here, the others to the original.

1. Prefix-Tuning: Optimizing Continuous Prompts for GenerationXiang Lisa Li, Percy Liang · Long Papers2,324 citations
2. Making Pre-trained Language Models Better Few-shot LearnersTianyu Gao, Adam Fisch, Danqi Chen · Long Papers1,254 citations · our summary
3. StereoSet: Measuring stereotypical bias in pretrained language modelsMoin Nadeem, Anna Bethke, Siva Reddy · Long Papers605 citations · our summary
4. LayoutLMv2: Multi-modal Pre-training for Visually-rich Document UnderstandingYang Xu, Yiheng Xu, Tengchao Lv et al. · Long Papers482 citations · our summary
5. ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation TransferYuanmeng Yan, Rumei Li, Sirui Wang et al. · Long Papers474 citations · our summary
6. ARBERT & MARBERT: Deep Bidirectional Transformers for ArabicMuhammad Abdul-Mageed, AbdelRahim Elmadany, El Moatez Billah Nagoudi · Long Papers397 citations
7. Dual Graph Convolutional Networks for Aspect-based Sentiment AnalysisRuifan Li, Hao Chen, Fangxiang Feng et al. · Long Papers374 citations · our summary
8. DeCLUTR: Deep Contrastive Learning for Unsupervised Textual RepresentationsJohn Giorgi, Osvald Nitski, Bo Wang et al. · Long Papers350 citations · our summary
9. Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-TuningArmen Aghajanyan, Sonal Gupta, Luke Zettlemoyer · Long Papers · 🏆 Outstanding Paper335 citations · our summary
10. VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and InterpretationChanghan Wang, Morgane Riviere, Ann Lee et al. · Long Papers329 citations · our summary

All accepted papers (795)

The most cited first; 89 with our summary link to their page here, the others to the original.

1. Prefix-Tuning: Optimizing Continuous Prompts for GenerationXiang Lisa Li, Percy Liang · Long Papers2,324 citations
2. Making Pre-trained Language Models Better Few-shot LearnersTianyu Gao, Adam Fisch, Danqi Chen · Long Papers1,254 citations · our summary
3. StereoSet: Measuring stereotypical bias in pretrained language modelsMoin Nadeem, Anna Bethke, Siva Reddy · Long Papers605 citations · our summary
4. LayoutLMv2: Multi-modal Pre-training for Visually-rich Document UnderstandingYang Xu, Yiheng Xu, Tengchao Lv et al. · Long Papers482 citations · our summary
5. ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation TransferYuanmeng Yan, Rumei Li, Sirui Wang et al. · Long Papers474 citations · our summary
6. ARBERT & MARBERT: Deep Bidirectional Transformers for ArabicMuhammad Abdul-Mageed, AbdelRahim Elmadany, El Moatez Billah Nagoudi · Long Papers397 citations
7. Dual Graph Convolutional Networks for Aspect-based Sentiment AnalysisRuifan Li, Hao Chen, Fangxiang Feng et al. · Long Papers374 citations · our summary
8. DeCLUTR: Deep Contrastive Learning for Unsupervised Textual RepresentationsJohn Giorgi, Osvald Nitski, Bo Wang et al. · Long Papers350 citations · our summary
9. Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-TuningArmen Aghajanyan, Sonal Gupta, Luke Zettlemoyer · Long Papers · 🏆 Outstanding Paper335 citations · our summary
10. VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and InterpretationChanghan Wang, Morgane Riviere, Ann Lee et al. · Long Papers329 citations · our summary
11. MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in ConversationJingwen Hu, Yuchen Liu, Jinming Zhao et al. · Long Papers326 citations
12. Cross-modal Memory Networks for Radiology Report GenerationZhihong Chen, Yaling Shen, Yan Song et al. · Long Papers321 citations
13. A Unified Generative Framework for Aspect-based Sentiment AnalysisHang Yan, Junqi Dai, Tuo Ji et al. · Long Papers298 citations · our summary
14. All That's `Human' Is Not Gold: Evaluating Human Evaluation of Generated TextElizabeth Clark, Tal August, Sofia Serrano et al. · Long Papers · 🏆 Outstanding Paper275 citations
15. Directed Acyclic Graph Network for Conversational Emotion RecognitionWeizhou Shen, Siyue Wu, Yunyi Yang et al. · Long Papers274 citations · our summary
16. Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic CoherenceFederico Bianchi, Silvia Terragni, Dirk Hovy · Short Papers269 citations · our summary
17. A Unified Generative Framework for Various NER SubtasksHang Yan, Tao Gui, Junqi Dai et al. · Long Papers267 citations · our summary
18. PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple ExtractionHengyi Zheng, Rui Wen, Xi Chen et al. · Long Papers244 citations
19. DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in ConversationsDou Hu, Lingwei Wei, Xiaoyong Huai · Long Papers238 citations
20. UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive LearningWei Li, Can Gao, Guocheng Niu et al. · Long Papers231 citations · our summary
21. Missing Modality Imagination Network for Emotion Recognition with Uncertain Missing ModalitiesJinming Zhao, Ruichen Li, Qin Jin · Long Papers229 citations
22. Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event ExtractionYaojie Lu, Hongyu Lin, Jin Xu et al. · Long Papers229 citations · our summary
23. WARP: Word-level Adversarial ReProgrammingKaren Hambardzumyan, Hrant Khachatrian, Jonathan May · Long Papers227 citations
24. Towards Emotional Support Dialog SystemsSiyang Liu, Chujie Zheng, Orianna Demasi et al. · Long Papers216 citations · our summary
25. Few-NERD: A Few-shot Named Entity Recognition DatasetNing Ding, Guangwei Xu, Yulin Chen et al. · Long Papers212 citations · our summary

See all 795 papers in ACL 2021 — accepted papers →

📄 Papers with our summary in our library (89)

The most cited first (OpenAlex citations plus our library's).

1. Making Pre-trained Language Models Better Few-shot LearnersTianyu Gao, Adam Fisch, Danqi Chen2021 · 1,963 citations
2. StereoSet: Measuring stereotypical bias in pretrained language modelsMoin Nadeem, Anna Bethke, Siva Reddy2021 · 1,132 citations
3. ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation TransferYuanmeng Yan, Rumei Li, Sirui Wang, et al.2021 · 648 citations
4. LayoutLMv2: Multi-modal Pre-training for Visually-rich Document UnderstandingYang Xu, Yiheng Xu, Tengchao Lv, et al.2021 · 623 citations
5. Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-TuningArmen Aghajanyan, Sonal Gupta, Luke Zettlemoyer2021 · 531 citations
6. VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and InterpretationChanghan Wang, Morgane Riviere, Ann Lee, et al.2021 · 524 citations
7. DeCLUTR: Deep Contrastive Learning for Unsupervised Textual RepresentationsJohn Giorgi, Osvald Nitski, Bo Wang, et al.2021 · 515 citations
8. How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language ModelsPhillip Rust, Jonas Pfeiffer, Ivan Vulić, et al.2021 · 444 citations
9. Dual Graph Convolutional Networks for Aspect-based Sentiment AnalysisRuifan Li, Hao Chen, Fangxiang Feng, et al.2021 · 429 citations
10. DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-ExpertsAlisa Liu, Maarten Sap, Ximing Lu, et al.2021 · 400 citations
11. TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in FinanceFengbin Zhu, Wenqiang Lei, Youcheng Huang, et al.2021 · 397 citations
12. A Unified Generative Framework for Aspect-based Sentiment AnalysisHang Yan, Junqi Dai, Tuo Ji, et al.2021 · 396 citations
13. A Unified Generative Framework for Various NER SubtasksHang Yan, Tao Gui, Junqi Dai, et al.2021 · 392 citations
14. Towards Emotional Support Dialog SystemsSiyang Liu, Chujie Zheng, Orianna Demasi, et al.2021 · 391 citations
15. Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event ExtractionYaojie Lu, Hongyu Lin, Jin Xu, et al.2021 · 370 citations
16. Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic CoherenceFederico Bianchi, Silvia Terragni, Dirk Hovy2021 · 366 citations
17. Parameter-Efficient Transfer Learning with Diff PruningDemi Guo, Alexander Rush, Yoon Kim2021 · 357 citations
18. Directed Acyclic Graph Network for Conversational Emotion RecognitionWeizhou Shen, Siyue Wu, Yunyi Yang, et al.2021 · 345 citations
19. SimCLS: A Simple Framework for Contrastive Learning of Abstractive SummarizationYixin Liu, Pengfei Liu2021 · 341 citations
20. Few-NERD: A Few-shot Named Entity Recognition DatasetNing Ding, Guangwei Xu, Yulin Chen, et al.2021 · 335 citations
21. Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate DetectionBertie Vidgen, Tristan Thrush, Zeerak Waseem, et al.2021 · 320 citations
22. UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive LearningWei Li, Can Gao, Guocheng Niu, et al.2021 · 299 citations
23. Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving ModelsTongshuang Wu, Marco Tulio Ribeiro, Jeffrey Heer, et al.2021 · 272 citations
24. Contrastive Learning for Many-to-many Multilingual Neural Machine TranslationXiao Pan, Mingxuan Wang, Liwei Wu, et al.2021 · 256 citations
25. Aspect-Category-Opinion-Sentiment Quadruple Extraction with Implicit Aspects and OpinionsHongjie Cai, Rui Xia, Jianfei Yu2021 · 255 citations

See all 89 works in ACL 2021 — accepted papers →

🧭 Top topics

Topics of its works in our library, with the number of works on each.

🧠Language models & pretraining (13)🌍Multilingual & cross-lingual NLP (12)😊Sentiment & emotion (10)🔁Machine translation (6)❓Question answering (6)🗨️Dialogue systems (6)🧮Reasoning (5)🛡️Bias, fairness & safety (5)English (5)🏷️Named entity recognition (4)🔗Coreference resolution (4)🔎Information extraction (4)🎙️Speech & spoken language (4)🧵Discourse analysis (3)📏Evaluation & benchmarks (3)

📚 Fields

🖥️Computer Science (89)🎭Arts and Humanities (84)🤝Social Sciences (12)💭Psychology (4)🧬Biochemistry, Genetics and Molecular Biology (2)🧠Neuroscience (1)

🧑‍🔬 Top authors

Authors with a page who published here most often: their works here, and the citations of those works.

🏛️ Top institutions

Institutions on the bylines of its works here, by the number of works.

🏢Alibaba DAMO AcademyHangzhou · China7 works here🏢Alibaba GroupHangzhou · China7 works here🎓University of WashingtonSeattle · United States6 works here🏢TencentShenzhen · China6 works here🏢MetaMenlo Park · United States6 works here🎓Tsinghua UniversityBeijing · China5 works here🏛️Chinese Academy of SciencesBeijing · China4 works here🏢Alibaba Group (Cayman Islands)George Town · Cayman Islands4 works here🔬Allen Institute for Artificial IntelligenceSeattle · United States4 works here🎓University of Chinese Academy of SciencesBeijing · China4 works here🎓Carnegie Mellon UniversityPittsburgh · United States4 works here🏢GoogleMountain View · United States3 works here

Place and dates from the event's site or the ACL Anthology; works and citations from OpenAlex and our library.

↑ back to top

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