本项目收集了各大顶会获奖论文（自2017年起），包括最佳论文、最佳demo论文、提名奖等，其中部分参考了Awesome-Best-Papers项目（包括自2013年起最佳论文）。逐步完善中，也欢迎大家共同参与到这个项目中来 ☺
This repo collects award-winning papers from major top conferences (since 2017), including best papers, best demo papers, nominations, etc., with some references to the Awesome-Best-Papers(including the best papers since 2013). Gradually improving, but also welcome to participate in this repo together ☺
| Domain | Conferences |
|---|---|
| Natural Language Processing | ACL, EMNLP, NAACL |
| Cross-domain | AAAI, IJCAI, NeurIPS, ICML, ICLR, WWW |
| Computer Vision | CVPR, ICCV, ECCV |
| Year | Award | Paper |
|---|---|---|
| 2021 | best paper | Vocabulary learning via optimal transport for neural machine translation Jingjing Xu (ByteDance AI Lab), Hao Zhou (ByteDance AI Lab), Chun Gan (ByteDance AI Lab; University of Wisconsin–Madison), Zaixiang Zheng (ByteDance AI Lab; Nanjing University) and Lei Li (ByteDance AI Lab) |
| 2021 | best theme paper | Including signed languages in natural language processing Kayo Yin (Carnegie Mellon University), Amit Moryossef (Bar-Ilan University), Julie Hochgesang (Gallaudet University), Yoav Goldberg (Bar-Ilan University; Allen Institute for AI) and Malihe Alikhani (University of Pittsburgh) |
| 2021 | outstanding paper | 1. All That's' Human'Is Not Gold: Evaluating Human Evaluation of Generated Text Elizabeth Clark (University of Washington), Tal August (University of Washington), Sofia Serrano (University of Washington), Nikita Haduong (University of Washington), Suchin Gururangan (University of Washington) and Noah A. Smith (University of Washington; Allen Institute for AI) 2. Intrinsic dimensionality explains the effectiveness of language model fine-tuning Armen Aghajanyan (Facebook), Sonal Gupta (Facebook) and Luke Zettlemoyer (Facebook) 3. Mind your outliers! investigating the negative impact of outliers on active learning for visual question answering Siddharth Karamcheti (Stanford University), Ranjay Krishna (Stanford University), Li Fei-Fei (Stanford University) and Christopher Manning (Stanford University) 4. Neural machine translation with monolingual translation memory Deng Cai (The Chinese University of Hong Kong), Yan Wang (Tencent AI Lab), Huayang Li (Tencent AI Lab), Wai Lam (The Chinese University of Hong Kong) and Lemao Liu (Tencent AI Lab) 5. Scientific credibility of machine translation research: A meta-evaluation of 769 papers Benjamin Marie (National Institute of Information and Communications Technology), Atsushi Fujita (National Institute of Information and Communications Technology) and Raphael Rubino (National Institute of Information and Communications Technology) 6. Unnatural language inference Koustuv Sinha (McGill University; Mila; FAIR), Prasanna Parthasarathi (McGill University; Mila), Joelle Pineau (McGill University; Mila; FAIR) and Adina Williams (FAIR) |
| 2020 | best paper | Beyond Accuracy: Behavioral Testing of NLP Models with CheckList Marco Tulio Ribeiro (Microsoft Research), Tongshuang Wu (University of Washington), Carlos Guestrin (University of Washington) and Sameer Singh (University of Washington) |
| 2020 | honorable mention paper (main conference) | 1. Don't stop pretraining: adapt language models to domains and tasks Suchin Gururangan (Allen Institute for Artificial Intelligence), Ana Marasović (Allen Institute for Artificial Intelligence; University of Washington), Swabha Swayamdipta (Allen Institute for Artificial Intelligence), Kyle Lo (Allen Institute for Artificial Intelligence), Iz Beltagy (Allen Institute for Artificial Intelligence), Doug Downey (Allen Institute for Artificial Intelligence) and Noah A. Smith (Allen Institute for Artificial Intelligence; University of Washington) 2. Tangled up in BLEU: Reevaluating the evaluation of automatic machine translation evaluation metrics Nitika Mathur (The University of Melbourne), Timothy Baldwin (The University of Melbourne) and Trevor Cohn (The University of Melbourne) |
| 2020 | best theme paper | Climbing towards NLU: On meaning, form, and understanding in the age of data Emily M. Bender (University of Washington) and Alexander Koller (Saarland University) |
| 2020 | honorable mention paper (theme) | How can we accelerate progress towards human-like linguistic generalization? Tal Linzen (Johns Hopkins University) |
| 2020 | best demonstration paper | Gaia: A fine-grained multimedia knowledge extraction system Manling Li (University of Illinois at Urbana-Champaign), Alireza Zareian (Columbia University), Ying Lin (University of Illinois at Urbana-Champaign), Xiaoman Pan (University of Illinois at Urbana-Champaign), Spencer Whitehead (University of Illinois at Urbana-Champaign), BRIAN CHEN (Columbia University), Bo Wu (Columbia University), Heng Ji (University of Illinois at Urbana-Champaign), Shih-Fu Chang (Columbia University), Clare Voss (US Army Research Laboratory), Daniel Napierski (Information Sciences Institute) and Marjorie Freedman (Information Sciences Institute) |
| 2020 | honorable mention paper (demonstrations) | 1. Torch-struct: Deep structured prediction library Alexander Rush (Cornell University) 2. Prta: A System to Support the Analysis of Propaganda Techniques in the News Giovanni Da San Martino (Qatar Computing Research Institute), Shaden Shaar (Qatar Computing Research Institute), Yifan Zhang (Qatar Computing Research Institute), Seunghak Yu (MIT Computer Science and Artificial Intelligence Laboratory), Alberto Barrón-Cedeño (Universita di Bologna) and Preslav Nakov (Qatar Computing Research Institute) |
| 2019 | best long paper | Bridging the Gap between Training and Inference for Neural Machine Translation Wen Zhang (University of Chinese Academy of Sciences), Yang Feng (University of Chinese Academy of Sciences), Fandong Meng (WeChat AI), Di You (Worcester Polytechnic Institute) and Qun Liu (Huawei Noah’s Ark Lab) |
| 2019 | best short paper | Do you know that Florence is packed with visitors? Evaluating state-of-the-art models of speaker commitment Nanjiang Jiang (The Ohio State University) and Marie-Catherine de Marneffe (The Ohio State University) |
| 2019 | best demo paper | OpenKiwi: An open source framework for quality estimation Fabio Kepler (Unbabel), Jonay Trenous (Unbabel), Marcos Treviso (Instituto de Telecomunicac¸oes), Miguel Vera (Unbabel) and André F. T. Martins (Unbabel) |
| 2019 | outstanding paper | 1. Emotion-cause pair extraction: A new task to emotion analysis in texts Rui Xia (Nanjing University of Science and Technology) and Zixiang Ding (Nanjing University of Science and Technology) 2. A simple theoretical model of importance for summarization Maxime Peyrard (EPFL) 3. Transferable multi-domain state generator for task-oriented dialogue systems Chien-Sheng Wu (The Hong Kong University of Science and Technology), Andrea Madotto (The Hong Kong University of Science and Technology), Ehsan Hosseini-Asl (Salesforce Research), Caiming Xiong (Salesforce Research), Richard Socher (Salesforce Research) and Pascale Fung (The Hong Kong University of Science and Technology) 4. We need to talk about standard splits Kyle Gorman (City University of New York) and Steven Bedrick (Oregon Health & Science University) 5. Zero-shot word sense disambiguation using sense definition embeddings Sawan Kumar (Indian Institute of Science), Sharmistha Jat (Indian Institute of Science), Karan Saxena (Carnegie Mellon University) and Partha Talukdar (Indian Institute of Science) |
| 2018 | best long paper | 1. Finding syntax in human encephalography with beam search John Hale (Cornell University), Chris Dyer (DeepMind); Adhiguna Kuncoro (University of Oxford) and Jonathan R. Brennan (University of Michigan) 2. Learning to ask good questions: Ranking clarification questions using neural expected value of perfect information Sudha Rao (University of Maryland) and Hal Daumé III (University of Maryland; Microsoft Research) 3. Let's do it" again": A First Computational Approach to Detecting Adverbial Presupposition Triggers Yulan Feng (McGill University; Mila), Jad Kabbara (McGill University; Mila) and Jackie Chi Kit Cheung (McGill University; Mila) |
| 2018 | best long paper honourable mention | 1. Coarse-to-fine decoding for neural semantic parsing Li Dong (University of Edinburgh) and Mirella Lapata (University of Edinburgh) 2. NASH: Toward end-to-end neural architecture for generative semantic hashing Dinghan Shen (Duke University), Qinliang Su (Sun Yat-sen University), Paidamoyo Chapfuwa (Duke University), Wenlin Wang (Duke University), Guoyin Wang (Duke University), Ricardo Henao (Duke University) and Lawrence Carin (Duke University) 3. Backpropagating through structured argmax using a SPIGOT Hao Peng (University of Washington), Sam Thomson (Carnegie Mellon University) and Noah A. Smith (University of Washington) 4. Hierarchical neural story generation Angela Fan (Facebook AI Research), Mike Lewis (Facebook AI Research) and Yann Dauphin (Facebook AI Research) 5. Semantically equivalent adversarial rules for debugging NLP models Marco Tulio Ribeiro (University of Washington), Sameer Singh (University of California) and Carlos Guestrin (University of Washington) 6. Large-scale QA-SRL parsing Nicholas FitzGerald (University of Washington), Julian Michael (University of Washington), Luheng He (University of Washington) and Luke Zettlemoyer (University of Washington) |
| 2018 | best short paper | 1. Know what you don't know: Unanswerable questions for SQuAD Pranav Rajpurkar (Stanford University), Robin Jia (Stanford University) and Percy Liang (Stanford University) 2. 'lighter'can still be dark: Modeling comparative color descriptions Olivia Winn (Columbia University) and Smaranda Muresan (Columbia University) |
| 2018 | best short paper honourable mention | 1. Jointly predicting predicates and arguments in neural semantic role labeling Luheng He (University of Washington), Kenton Lee (University of Washington), Omer Levy and Luke Zettlemoyer (University of Washington) 2. Do neural network cross-modal mappings really bridge modalities? Guillem Collell (KU Leuven) and Marie-Francine Moens (KU Leuven) |
| 2017 | best paper | Probabilistic Typology: Deep Generative Models of Vowel Inventories Ryan Cotterell (Johns Hopkins University) and Jason Eisner (Johns Hopkins University) |
| Year | Award | Paper |
|---|---|---|
| 2021 | best long paper | Visually Grounded Reasoning across Languages and Cultures Fangyu Liu (University of Cambridge), Emanuele Bugliarello (University of Copenhagen), Edoardo Maria Ponti (Mila – Quebec Artifcial Intelligence Institute; McGill University), Siva Reddy (Mila – Quebec Artifcial Intelligence Institute; McGill University), Nigel Collier (University of Cambridge) and Desmond Elliott (University of Copenhagen) |
| 2021 | best short paper | CHoRaL: Collecting Humor Reaction Labels from Millions of Social Media Users Zixiaofan Yang (Columbia University), Shayan Hooshmand (Columbia University) and Julia Hirschberg (Columbia University) |
| 2021 | outstanding paper | 1. Mindcraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks Cristian-Paul Bara (University of Michigan), Sky CH-Wang (Columbia University) and Joyce Chai (University of Michigan) 2. Situatedqa: Incorporating extra-linguistic contexts into QA Michael Zhang (The University of Texas at Austin) and Eunsol Choi (The University of Texas at Austin) 3. When attention meets fast recurrence: Training language models with reduced compute Tao Lei (ASAPP) 4. Shortcutted commonsense: Data spuriousness in deep learning of commonsense reasoning Ruben Branco (University of Lisbon), Antonio Branco (University of Lisbon), Joao Antonio Rodrigues (University of Lisbon) and Joao Ricardo Silva (University of Lisbon) |
| 2021 | best demonstration paper | Datasets: A community library for natural language processing Quentin Lhoest, Albert Villanova del Moral, Yacine Jernite, Abhishek Thakur, Patrick von Platen, Suraj Patil, Julien Chaumond, Mariama Drame, Julien Plu, Lewis Tunstall, Joe Davison, Mario Šaško, Gunjan Chhablani, Bhavitvya Malik, Simon Brandeis, Teven Le Scao, Victor Sanh, Canwen Xu, Nicolas Patry, Angelina McMillan-Major, Philipp Schmid, Sylvain Gugger, Clément Delangue, Théo Matussière, Lysandre Debut, Stas Bekman, Pierric Cistac, Thibault Goehringer, Victor Mustar, François Lagunas, Alexander Rush and Thomas Wolf |
| 2020 | best paper | Digital voicing of Silent Speech David Gaddy (University of California, Berkeley); Dan Klein (University of California, Berkeley) |
| 2020 | honourable mention paper | 1. If beam search is the answer, what was the question? Clara Meister (ETH Zurich), Ryan Cotterell (Johns Hopkins University) and Tim Vieira (University of Cambridge; ETH Zurich) 2. Glucose: Generalized and contextualized story explanations Nasrin Mostafazadeh (Elemental Cognition), Aditya Kalyanpur (Elemental Cognition), Lori Moon (Elemental Cognition), David Buchanan (Elemental Cognition), Lauren Berkowitz (Elemental Cognition), Or Biran (Elemental Cognition) and Jennifer Chu-Carroll (Elemental Cognition) 3. Spot the bot: A robust and efficient framework for the evaluation of conversational dialogue systems Jan Deriu (ZHAW), Don Tuggener (ZHAW), Pius von Däniken (ZHAW), Jon Ander Campos (UPV/EHU), Alvaro Rodrigo (UNED), Thiziri Belkacem (Synapse Developpement), Aitor Soroa (UPV/EHU), Eneko Agirre (UPV/EHU) and Mark Cieliebak (ZHAW) 4. Visually grounded compound PCFGs Yanpeng Zhao (University of Edinburgh) and Ivan Titov (University of Amsterdam) |
| 2020 | best demonstration paper | Transformers: State-of-the-art natural language processing Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, Alexander M. Rush |
| 2019 | best paper | Specializing Word Embeddings (for Parsing) by Information Bottleneck Xiang Lisa Li (Johns Hopkins University); Jason Eisner (Johns Hopkins University) |
| 2018 | best paper | Linguistically-Informed Self-Attention for Semantic Role Labeling Emma Strubell (University of Massachusetts Amherst); Patrick Verga (University of Massachusetts Amherst); Daniel Andor (Google AI Language); David Weiss (Google AI Language); Andrew McCallum (University of Massachusetts Amherst) |
| 2017 | best paper | 1. Depression and Self-Harm Risk Assessment in Online Forums Andrew Yates (Max Planck Institute for Informatics); Arman Cohan (Georgetown University); Nazli Goharian (Georgetown University) 2. Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints Jieyu Zhao (University of Virginia); Tianlu Wang (University of Virginia); Mark Yatskar (University of Washington); Vicente Ordonez (University of Virginia); Kai-Wei Chang (University of Virginia) |
| Year | Award | Paper |
|---|---|---|
| 2021 | best long paper | Video-aided unsupervised grammar induction Songyang Zhang (University of Rochester), Linfeng Song (Tencent AI Lab), Lifeng Jin (Tencent AI Lab), Kun Xu (Tencent AI Lab), Dong Yu (Tencent AI Lab) and Jiebo Luo (University of Rochester) |
| 2021 | outstanding long paper | 1. Unifying cross-lingual Semantic Role Labeling with heterogeneous linguistic resources Simone Conia (Sapienza University of Rome), Andrea Bacciu (Sapienza University of Rome) and Roberto Navigli (Sapienza University of Rome) 2. It's not just size that matters: Small language models are also few-shot learners Timo Schick (Center for Information and Language Processing; Sulzer GmbH) and Hinrich Schütze (Center for Information and Language Processing) |
| 2021 | best short paper | Learning how to ask: Querying LMs with mixtures of soft prompts Guanghui Qin ( Johns Hopkins University) and Jason Eisner ( Johns Hopkins University) |
| 2021 | outstanding short paper | How many data points is a prompt worth? Teven Le Scao (Hugging Face) and Alexander Rush (Hugging Face) |
| 2021 | best thematic paper | Preregistering NLP research Emiel van Miltenburg (Tilburg University), Chris van der Lee (Tilburg University) and Emiel Krahmer (Tilburg University) |
| 2019 | best paper | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding Jacob Devlin (Google AI Language); Ming-Wei Chang (Google AI Language); Kenton Lee (Google AI Language); Kristina Toutanova (Google AI Language) |
| 2018 | best paper | Deep contextualized word representations Matthew E. Peters (Allen Institute for Artificial Intelligence); Mark Neumann (Allen Institute for Artificial Intelligence); Mohit Iyyer (Allen Institute for Artificial Intelligence); Matt Gardner (Allen Institute for Artificial Intelligence); Christopher Clark (University of Washington); Kenton Lee (University of Washington); Luke Zettlemoyer (Allen Institute for Artificial Intelligence) |
| Year | Award | Paper |
|---|---|---|
| 2021 | outstanding paper award | 1. Informer: Beyond efficient transformer for long sequence time-series forecasting Haoyi Zhou (Beihang University), Shanghang Zhang (UC Berkeley), Jieqi Peng (Beihang University), Shuai Zhang (Beihang University), Jianxin Li (Beihang University), Hui Xiong (Rutgers University), Wancai Zhang (Beijing Guowang Fuda Science & Technology Development Company) 2. Exploration-exploitation in multi-agent learning: Catastrophe theory meets game theory Stefanos Leonardos (Singapore University of Technology and Design), Georgios Piliouras (Singapore University of Technology and Design) |
| 2021 | honorable mention | 1. Learning from extreme bandit feedback Romain Lopez (University of California), Inderjit S. Dhillon (University of Texas at Austin; Amazon Inc), Michael Jordan (University of California) 2. Self-attention attribution: Interpreting information interactions inside transformer Yaru Hao (Beihang University), Li Dong (Microsoft Research), Furu Wei (Microsoft Research), Ke Xu (Beihang University) |
| 2021 | diatinguished paper | 1. IQ–Incremental Learning for Solving QSAT Thomas L Lee (University of Cambridge), Viktor Tóth (University of Cambridge), Sean B Holden (University of Cambridge) 2. Ethically compliant sequential decision making Justin Svegliato (University of Massachusetts Amherst), Samer Nashed (University of Massachusetts Amherst), Shlomo Zilberstein (University of Massachusetts Amherst) 3. On the tractability of SHAP explanations Guy Van den Broeck (University of California), Anton Lykov (University of California), Maximilian Schleich (University of Washington), Dan Suciu (University of Washington) 4. Expected eligibility traces Hado van Hasselt (DeepMind), Sephora Madjiheurem (University College London), Matteo Hessel (DeepMind), Andre Barreto (DeepMind), David Silver (DeepMind), Diana Borsa (DeepMind) 5. Polynomial-time algorithms for counting and sampling Markov equivalent dags Marcel Wienöbst (University of Lubeck), Max Bannach (University of Lubeck), Maciej Liskiewicz (University of Lubeck) 6. Self-supervised multi-view stereo via effective co-segmentation and data-augmentation Hongbin Xu (Chinese Academy of Sciences; South China University of Technology), Zhipeng Zhou (Chinese Academy of Sciences), Yu Qiao (Chinese Academy of Sciences; Shanghai AI Lab), Wenxiong Kang (South China University of Technology), Qiuxia Wu (South China University of Technology) |