📰 EMNLP 2021 — accepted papers

EMNLP 2021 is the 2021 edition of the Conference on Empirical Methods in Natural Language Processing (EMNLP), held in Online and Punta Cana, Dominican Republic, November 2021 (publisher: Association for Computational Linguistics). The ACL Anthology lists 895 papers of it in 3 tracks; our library holds 70 with our summaries. Below: the most cited papers, every accepted paper, and ours with their topics, authors and institutions.

Tracks

Main847System Demonstrations42Tutorial Abstracts6

Most cited papers

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

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

All accepted papers (895)

The most cited first; 70 with our summary link to their page here, the others to the original.

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

See all 895 papers in EMNLP 2021 — accepted papers →

📄 Papers with our summary in our library (70)

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

1. SimCSE: Simple Contrastive Learning of Sentence EmbeddingsTianyu Gao, Xingcheng Yao, Danqi Chen2021 · 3,922 citations
2. CLIPScore: A Reference-free Evaluation Metric for Image CaptioningJack Hessel, Ari Holtzman, Maxwell Forbes, et al.2021 · 1,499 citations
3. Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment AnalysisWei Han, Hui Chen, Soujanya Poria2021 · 564 citations
4. FinQA: A Dataset of Numerical Reasoning over Financial DataZhiyu Chen, Wenhu Chen, Charese Smiley, et al.2021 · 511 citations
5. Latent Hatred: A Benchmark for Understanding Implicit Hate SpeechMai ElSherief, Caleb Ziems, David Muchlinski, et al.2021 · 365 citations
6. QuestEval: Summarization Asks for Fact-based EvaluationThomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, et al.2021 · 354 citations
7. Aspect Sentiment Quad Prediction as Paraphrase GenerationWenxuan Zhang, Yang Deng, Xin Li, et al.2021 · 325 citations
8. Muppet: Massive Multi-task Representations with Pre-FinetuningArmen Aghajanyan, Anchit Gupta, Akshat Shrivastava, et al.2021 · 299 citations
9. Entity-Based Knowledge Conflicts in Question AnsweringShayne Longpre, Kartik Perisetla, Anthony Chen, et al.2021 · 295 citations
10. AdapterDrop: On the Efficiency of Adapters in TransformersAndreas Rücklé, Gregor Geigle, Max Glockner, et al.2021 · 295 citations
11. Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for LittleKoustuv Sinha, Robin Jia, Dieuwke Hupkes, et al.2021 · 292 citations
12. ONION: A Simple and Effective Defense Against Textual Backdoor AttacksFanchao Qi, Yangyi Chen, Mukai Li, et al.2021 · 279 citations
13. XTREME-R: Towards More Challenging and Nuanced Multilingual EvaluationSebastian Ruder, Noah Constant, Jan Botha, et al.2021 · 277 citations
14. Surface Form Competition: Why the Highest Probability Answer Isn't Always RightAri Holtzman, Peter West, Vered Shwartz, et al.2021 · 271 citations
15. Condenser: a Pre-training Architecture for Dense RetrievalLuyu Gao, Jamie Callan2021 · 261 citations
16. CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive SummarizationShuyang Cao, Lu Wang2021 · 258 citations
17. RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingRuiyang Ren, Yingqi Qu, Jing Liu, et al.2021 · 256 citations
18. Generating Datasets with Pretrained Language ModelsTimo Schick, Hinrich Schutze2021 · 250 citations
19. Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language TechnologiesSunipa Dev, Masoud Monajatipoor, Anaelia Ovalle, et al.2021 · 228 citations
20. Measuring Association Between Labels and Free-Text RationalesSarah Wiegreffe, Ana Marasović, Noah A. Smith2021 · 215 citations
21. Explaining Answers with Entailment TreesBhavana Dalvi, Peter Jansen, Oyvind Tafjord, et al.2021 · 207 citations
22. Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuningRunxin Xu, Fuli Luo, Zhiyuan Zhang, et al.2021 · 200 citations
23. Block Pruning For Faster TransformersFrançois Lagunas, Ella Charlaix, Victor Sanh, et al.2021 · 197 citations
24. Q²: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question AnsweringOr Honovich, Leshem Choshen, Roee Aharoni, et al.2021 · 195 citations
25. Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style TransferFanchao Qi, Yangyi Chen, Xurui Zhang, et al.2021 · 188 citations

See all 70 works in EMNLP 2021 — accepted papers →

🧭 Top topics

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

🧠Language models & pretraining (11)😊Sentiment & emotion (9)🔗Coreference resolution (7)🌍Multilingual & cross-lingual NLP (7)📝Summarization (4)📏Evaluation & benchmarks (4)🔍Information retrieval & search (4)❓Question answering (3)✍️Text generation (3)🗨️Dialogue systems (3)🧮Reasoning (3)🖼️Vision & language (3)🪶Efficient models & compression (3)🧵Discourse analysis (2)🔁Machine translation (2)

📚 Fields

🖥️Computer Science (69)🎭Arts and Humanities (64)💭Psychology (3)🤝Social Sciences (3)🧬Biochemistry, Genetics and Molecular Biology (1)🧠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.

🎓Carnegie Mellon UniversityPittsburgh · United States5 works here🏢GoogleMountain View · United States4 works here🎓University of CambridgeCambridge · United Kingdom4 works here🎓Technische Universität DarmstadtDarmstadt · Germany4 works here🎓Hebrew University of JerusalemJerusalem · Israel3 works here🎓Princeton UniversityPrinceton · United States3 works here🎓University of WashingtonSeattle · United States3 works here🎓Paderborn UniversityPaderborn · Germany3 works here🎓University of California San DiegoSan Diego · United States3 works here🏢MetaMenlo Park · United States3 works here🔬Allen Institute for Artificial IntelligenceSeattle · United States3 works here🎓University of EdinburghEdinburgh · United Kingdom3 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/emnlp/2021/