📅 Papers of 2020 — page 1625 papers · all years1 2 … 7 next →Array Programming with NumPyCharles R. Harris, K. Jarrod Millman, Stéfan J. van der Walt, et al.Nature · 23,591 citationsEnd-to-End Object Detection with TransformersNicolas Carion, Francisco Massa, Gabriel Synnaeve, et al.Lecture notes in computer science · 16,761 citationsTransformers: State-of-the-Art Natural Language ProcessingThomas Wolf, Lysandre Debut, Victor Sanh, et al.Conference on Empirical Methods in Natural… · 15,591 citationsBART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, et al.Annual Meeting of the Association for… · 12,752 citationsLanguage Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, et al.arXiv:2005.14165 · 10,782 citationsA Simple Framework for Contrastive Learning of Visual RepresentationsTing Chen, Simon Kornblith, Mohammad Norouzi, et al.arXiv:2002.05709 · 7,774 citationsDense Passage Retrieval for Open-Domain Question AnsweringVladimir Karpukhin, Barlas Oguz, Sewon Min, et al.Conference on Empirical Methods in Natural… · 5,370 citationsMeasuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, et al.arXiv:2009.03300 · 3,489 citationsConformer: Convolution-augmented Transformer for Speech RecognitionAnmol Gulati, James Qin, Chung-Cheng Chiu, et al.Interspeech · 3,433 citationsCodeBERT: A Pre-Trained Model for Programming and Natural LanguagesZhangyin Feng, Daya Guo, Duyu Tang, et al.Findings of the Association for Computational… · 2,954 citationsDomain-Specific Language Model Pretraining for Biomedical Natural Language ProcessingYu Gu; Robert Tinn; Hao Cheng; Michael Lucas; Naoto Usuyama; Xiaodong Liu; Tristan Naumann; Jianfeng Gao;, Hoifung PoonarXiv:2007.15779 · 2,636 citationsStanza: A Python Natural Language Processing Toolkit for Many Human LanguagesPeng Qi, Yuhao Zhang, Yuhui Zhang, et al.English · 2,347 citationsA Primer in BERTology: What We Know About How BERT WorksAnna Rogers, Olga Kovaleva, Anna RumshiskyTransactions of the Association for… · 2,127 citationsKnowledge GraphsAidan Hogan, Eva Blomqvist, Michael Cochez, et al.ACM Computing Surveys · 2,011 citationsAn Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, et al.arXiv:2010.11929 · 1,947 citationsAutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated PromptsTaylor Shin, Yasaman Razeghi, Robert L. Logan IV, et al.Conference on Empirical Methods in Natural… · 1,879 citationsOscar: Object-Semantics Aligned Pre-training for Vision-Language TasksXiujun Li, Xi Yin, Chunyuan Li, et al.Lecture notes in computer science · 1,827 citationsScaling Laws for Neural Language ModelsJared Kaplan, Sam McCandlish, Tom Henighan, et al.arXiv:2001.08361 · 1,814 citationsDeBERTa: Decoding-enhanced BERT with Disentangled AttentionPengcheng He, Xiaodong Liu, Jianfeng Gao, et al.arXiv:2006.03654 · 1,800 citationsCOMET: A Neural Framework for MT EvaluationRicardo Rei, Craig Stewart, Ana C Farinha, et al.Machine translation · 1,784 citationsColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTOmar Khattab, Matei ZahariaInternational ACM SIGIR Conference on Research… · 1,776 citationsPre-trained Models for Natural Language Processing: A SurveyXipeng Qiu, Tianxiang Sun, Yige Xu, et al.arXiv:2003.08271 · SCIENCE CHINA Technological… · 1,740 citationsLongformer: The Long-Document TransformerIz Beltagy, Matthew E. Peters, Arman CohanarXiv:2004.05150 · 1,737 citationsLanguage (Technology) is Power: A Critical Survey of “Bias” in NLPSu Lin Blodgett, Solon Barocas, Hal Daumé III, et al.Annual Meeting of the Association for… · 1,700 citationsScore-Based Generative Modeling through Stochastic Differential EquationsYang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, et al.arXiv:2011.13456 · 1,528 citationsEfficient Transformers: A SurveyYi Tay, Mostafa Dehghani, Dara Bahri, et al.ACM Computing Surveys · 1,513 citationsHow Can We Know What Language Models Know?Zhengbao Jiang, Frank F. Xu, Jun Araki, et al.Transactions of the Association for… · 1,493 citationsThe State and Fate of Linguistic Diversity and Inclusion in the NLP WorldPratik Joshi, Sebastin Santy, Amar Budhiraja, et al.Annual Meeting of the Association for… · 1,492 citationsLEGAL-BERT: The Muppets straight out of Law SchoolIlias Chalkidis, Manos Fergadiotis, Prodromos Malakasiotis, et al.Findings of the Association for Computational… · 1,490 citationsLanguage-agnostic BERT Sentence EmbeddingFangxiaoyu Feng, Yinfei Yang, Daniel Cer, et al.Annual Meeting of the Association for… · 1,412 citationsClimbing towards NLU: On Meaning, Form, and Understanding in the Age of DataEmily M. Bender, Alexander KollerAnnual Meeting of the Association for… · 1,371 citationswav2vec 2.0: A Framework for Self-Supervised Learning of Speech RepresentationsAlexei Baevski, Henry Zhou, Abdelrahman Mohamed, et al.Conference on Neural Information Processing… · 1,355 citationsMaking Monolingual Sentence Embeddings Multilingual using Knowledge DistillationNils Reimers, Iryna GurevychConference on Empirical Methods in Natural… · 1,320 citationsAraBERT: Transformer-based Model for Arabic Language UnderstandingWissam Antoun, Fady Baly, Hazem HajjarXiv:2003.00104 · 1,297 citationsRealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language ModelsSamuel Gehman, Suchin Gururangan, Maarten Sap, et al.Findings of the Association for Computational… · 1,277 citationsOn the Cross-lingual Transferability of Monolingual RepresentationsMikel Artetxe, Sebastian Ruder, Dani YogatamaAnnual Meeting of the Association for… · 1,168 citationsBERTweet: A pre-trained language model for English TweetsDat Quoc Nguyen, Thanh Vu, Anh Tuan NguyenConference on Empirical Methods in Natural… · 1,139 citationsQuantifying Attention Flow in TransformersSamira Abnar, Willem ZuidemaAnnual Meeting of the Association for… · 1,049 citationsMobileBERT: a Compact Task-Agnostic BERT for Resource-Limited DevicesZhiqing Sun, Hongkun Yu, Xiaodan Song, et al.Annual Meeting of the Association for… · 1,003 citationsBig Bird: Transformers for Longer SequencesManzil Zaheer, Guru Guruganesh, Avinava Dubey, et al.Conference on Neural Information Processing… · 992 citationsTweetEval: Unified Benchmark and Comparative Evaluation for Tweet ClassificationFrancesco Barbieri, Jose Camacho-Collados, Leonardo Neves, et al.arXiv:2010.12421 · 952 citationsAdapterFusion: Non-Destructive Task Composition for Transfer LearningJonas Pfeiffer, Aishwarya Kamath, Andreas Rücklé, et al.arXiv:2005.00247 · Proceedings of EACL 2021 · 948 citationsMPNet: Masked and Permuted Pre-training for Language UnderstandingKaitao Song, Xu Tan, Tao Qin, et al.arXiv:2004.09297 · 944 citationsTopic Modeling in Embedding SpacesAdji B. Dieng, Francisco J. R. Ruiz, David M. BleiTransactions of the Association for… · 914 citationsExtracting Training Data from Large Language ModelsNicholas Carlini, Florian Tramer, Eric Wallace, et al.arXiv:2012.07805 · 901 citationsCrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language ModelsNikita Nangia, Clara Vania, Rasika Bhalerao, et al.Conference on Empirical Methods in Natural… · 886 citationsTextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLPJohn X. Morris, Eli Lifland, Jin Yong Yoo, et al.Conference on Empirical Methods in Natural… · 857 citationsTaPas: Weakly Supervised Table Parsing via Pre-trainingJonathan Herzig, Pawel Krzysztof Nowak, Thomas Müller, et al.Annual Meeting of the Association for… · 844 citationsUNIFIEDQA: Crossing Format Boundaries with a Single QA SystemDaniel Khashabi, Sewon Min, Tushar Khot, et al.Findings of the Association for Computational… · 843 citationsWhat BERT Is Not: Lessons from a New Suite of Psycholinguistic Diagnostics for Language ModelsAllyson EttingerTransactions of the Association for… · 843 citationsBERT-ATTACK: Adversarial Attack Against BERT Using BERTLinyang Li, Ruotian Ma, Qipeng Guo, et al.Conference on Empirical Methods in Natural… · 840 citationsA Unified MRC Framework for Named Entity RecognitionXiaoya Li, Jingrong Feng, Yuxian Meng, et al.Annual Meeting of the Association for… · 833 citationsMAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual TransferJonas Pfeiffer, Ivan Vulić, Iryna Gurevych, et al.Conference on Empirical Methods in Natural… · 831 citationsOn the Sentence Embeddings from Pre-trained Language ModelsBohan Li, Hao Zhou, Junxian He, et al.Conference on Empirical Methods in Natural… · 830 citationsDocVQA: A Dataset for VQA on Document ImagesMinesh Mathew, Dimosthenis Karatzas, C.V. JawahararXiv:2007.00398 · 820 citationsERASER: A Benchmark to Evaluate Rationalized NLP ModelsJay DeYoung, Sarthak Jain, Nazneen Fatema Rajani, et al.Annual Meeting of the Association for… · 820 citationsRevisiting Pre-Trained Models for Chinese Natural Language ProcessingYiming Cui, Wanxiang Che, Ting Liu, et al.arXiv:2004.13922 · 788 citationsRelational Graph Attention Network for Aspect-based Sentiment AnalysisKai Wang, Weizhou Shen, Yunyi Yang, et al.Annual Meeting of the Association for… · 775 citationsReformer: The Efficient TransformerNikita Kitaev, Łukasz Kaiser, Anselm LevskayaarXiv:2001.04451 · 774 citationsAdapterHub: A Framework for Adapting TransformersJonas Pfeiffer, Andreas Rücklé, Clifton Poth, et al.Conference on Empirical Methods in Natural… · 747 citationsTowards Faithfully Interpretable NLP Systems: How Should We Define and Evaluate Faithfulness?Alon Jacovi, Yoav GoldbergAnnual Meeting of the Association for… · 747 citationsIntegrating Multimodal Information in Large Pretrained TransformersWasifur Rahman, Md Kamrul Hasan, Sangwu Lee, et al.Annual Meeting of the Association for… · 742 citationsConstructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning StepsXanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, et al.International Conference on Computational… · 735 citationsDice Loss for Data-imbalanced NLP TasksXiaoya Li, Xiaofei Sun, Yuxian Meng, et al.Annual Meeting of the Association for… · 734 citationsA Novel Cascade Binary Tagging Framework for Relational Triple ExtractionZhepei Wei, Jianlin Su, Yue Wang, et al.Annual Meeting of the Association for… · 732 citationsIndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian LanguagesDivyanshu Kakwani, Anoop Kunchukuttan, Satish Golla, et al.Findings of the Association for Computational… · 730 citationsFact or Fiction: Verifying Scientific ClaimsDavid Wadden, Shanchuan Lin, Kyle Lo, et al.Conference on Empirical Methods in Natural… · 706 citationsTyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse LanguagesJonathan H. Clark, Eunsol Choi, Michael Collins, et al.Transactions of the Association for… · 691 citationsSPECTER: Document-level Representation Learning using Citation-informed TransformersArman Cohan, Sergey Feldman, Iz Beltagy, et al.Annual Meeting of the Association for… · 690 citationsTaBERT: Pretraining for Joint Understanding of Textual and Tabular DataPengcheng Yin, Graham Neubig, Wen-tau Yih, et al.Annual Meeting of the Association for… · 690 citationsCORD-19: The COVID-19 Open Research DatasetLucy Lu Wang, Kyle Lo, Yoganand Chandrasekhar, et al.Workshop on NLP for COVID-19 at ACL · 685 citationsApproximate Nearest Neighbor Negative Contrastive Learning for Dense Text RetrievalLee Xiong, Chenyan Xiong, Ye Li, et al.arXiv:2007.00808 · 681 citationsSocial Bias Frames: Reasoning about Social and Power Implications of LanguageMaarten Sap, Saadia Gabriel, Lianhui Qin, et al.Annual Meeting of the Association for… · 680 citationsImproving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base EmbeddingsApoorv Saxena, Aditay Tripathi, Partha TalukdarAnnual Meeting of the Association for… · 670 citationsBAE: BERT-based Adversarial Examples for Text ClassificationSiddhant Garg, Goutham RamakrishnanConference on Empirical Methods in Natural… · 665 citationsKILT: a Benchmark for Knowledge Intensive Language TasksFabio Petroni, Aleksandra Piktus, Angela Fan, et al.Conference of the North American Chapter of the… · 663 citationsK-Adapter: Infusing Knowledge into Pre-Trained Models with AdaptersRuize Wang, Duyu Tang, Nan Duan, et al.arXiv:2002.01808 · 662 citationsEfficient Content-Based Sparse Attention with Routing TransformersAurko Roy, Mohammad Saffar, Ashish Vaswani, et al.Transactions of the Association for… · 660 citationsCCNet: Extracting High Quality Monolingual Datasets from Web Crawl DataGuillaume Wenzek, Marie-Anne Lachaux, Alexis Conneau, et al.Language Resources and Evaluation Conference… · 650 citationsCodeSearchNet Challenge: Evaluating the State of Semantic Code SearchHamel Husain, Ho-Hsiang Wu, Tiferet Gazit, et al.arXiv:1909.09436 · 647 citationsA Frustratingly Easy Approach for Entity and Relation ExtractionZexuan Zhong, Danqi ChenConference of the North American Chapter of the… · 629 citationsEfficient Intent Detection with Dual Sentence EncodersIñigo Casanueva, Tadas Temčinas, Daniela Gerz, et al.Workshop on Natural Language Processing for… · 622 citationsScalable Zero-shot Entity Linking with Dense Entity RetrievalLedell Wu, Fabio Petroni, Martin Josifoski, et al.Conference on Empirical Methods in Natural… · 618 citationsEvent Extraction by Answering (Almost) Natural QuestionsXinya Du, Claire CardieConference on Empirical Methods in Natural… · 602 citationsA Joint Neural Model for Information Extraction with Global FeaturesYing Lin, Heng Ji, Fei Huang, et al.Annual Meeting of the Association for… · 600 citationsNamed Entity Recognition as Dependency ParsingJuntao Yu, Bernd Bohnet, Massimo PoesioAnnual Meeting of the Association for… · 594 citationsTowards a Human-like Open-Domain ChatbotDaniel Adiwardana, Minh-Thang Luong, David R. So, et al.arXiv:2001.09977 · 573 citationsMultilingual Universal Sentence Encoder for Semantic RetrievalYinfei Yang, Daniel Cer, Amin Ahmad, et al.Annual Meeting of the Association for… · 571 citationsPhoBERT: Pre-trained language models for VietnameseDat Quoc Nguyen, Anh Tuan NguyenFindings of the Association for Computational… · 571 citationsExtractive Summarization as Text MatchingMing Zhong, Pengfei Liu, Yiran Chen, et al.Annual Meeting of the Association for… · 567 citationsMIND: A Large-scale Dataset for News RecommendationFangzhao Wu, Ying Qiao, Jiun-Hung Chen, et al.Annual Meeting of the Association for… · 562 citationsXTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual GeneralizationJunjie Hu, Sebastian Ruder, Aditya Siddhant, et al.arXiv:2003.11080 · 551 citationsWhat Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical ExamsDi Jin, Eileen Pan, Nassim Oufattole, et al.arXiv:2009.13081 · 540 citationsDocument Ranking with a Pretrained Sequence-to-Sequence ModelRodrigo Nogueira, Zhiying Jiang, Ronak Pradeep, et al.Findings of the Association for Computational… · 538 citationsTPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair LinkingYucheng Wang, Bowen Yu, Yueyang Zhang, et al.International Conference on Computational… · 527 citationsEvaluating Models' Local Decision Boundaries via Contrast SetsMatt Gardner, Yoav Artzi, Victoria Basmov, et al.Mova's core list · 520 citationsHow Does NLP Benefit Legal System: A Summary of Legal Artificial IntelligenceHaoxi Zhong, Chaojun Xiao, Cunchao Tu, et al.Annual Meeting of the Association for… · 518 citationsMLS: A Large-Scale Multilingual Dataset for Speech ResearchVineel Pratap, Qiantong Xu, Anuroop Sriram, et al.Interspeech · 510 citationsFLAT: Chinese NER Using Flat-Lattice TransformerXiaonan Li, Hang Yan, Xipeng Qiu, et al.Annual Meeting of the Association for… · 503 citationsDeeBERT: Dynamic Early Exiting for Accelerating BERT InferenceJi Xin, Raphael Tang, Jaejun Lee, et al.Annual Meeting of the Association for… · 480 citations1 2 … 7 next →↑ back to topThis page in Markdown → https://md.research.elamur.ai/free/en/papers/2020/