{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1905.02175","title":"Adversarial Examples Are Not Bugs, They Are Features","created":"2019-05-06","cited_by_count":953},{"id":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1603.06560","title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","created":"2016-03-21","cited_by_count":699},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"id":"2011.03395","title":"Underspecification Presents Challenges for Credibility in Modern Machine Learning","created":"2020-11-06","cited_by_count":496},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"2003.03808","title":"PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models","created":"2020-03-08","cited_by_count":358},{"id":"2004.10643","title":"Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection","created":"2020-04-22","cited_by_count":271},{"id":"2111.07997","title":"Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection","created":"2021-11-15","cited_by_count":264},{"id":"2002.05651","title":"Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning","created":"2020-01-31","cited_by_count":249},{"id":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","cited_by_count":243},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203},{"id":"2103.03098","title":"Accounting for Variance in Machine Learning Benchmarks","created":"2021-03-01","cited_by_count":201},{"id":"2106.15590","title":"The Values Encoded in Machine Learning Research","created":"2021-06-29","cited_by_count":172},{"id":"1909.03004","title":"Show Your Work: Improved Reporting of Experimental Results","created":"2019-09-06","cited_by_count":169},{"id":"2007.03051","title":"Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models","created":"2020-07-06","cited_by_count":169},{"id":"2202.05924","title":"Compute Trends Across Three Eras of Machine Learning","created":"2022-02-11","cited_by_count":163},{"id":"2009.06489","title":"The Hardware Lottery","created":"2020-09-14","cited_by_count":160},{"id":"1811.12808","title":"Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning","created":"2018-11-13","cited_by_count":157},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155},{"id":"2010.15775","title":"Understanding the Failure Modes of Out-of-Distribution Generalization","created":"2020-10-29","cited_by_count":146},{"id":"2107.05847","title":"Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges","created":"2021-07-13","cited_by_count":145},{"id":"2101.10943","title":"Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithms","created":"2021-01-26","cited_by_count":144},{"id":"2010.06595","title":"With Little Power Comes Great Responsibility","created":"2020-10-13","cited_by_count":142},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136},{"id":"2110.05699","title":"On Releasing Annotator-Level Labels and Information in Datasets","created":"2021-10-12","cited_by_count":126},{"id":"2007.04068","title":"Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence","created":"2020-07-08","cited_by_count":101},{"id":"1904.08783","title":"Evaluating the Underlying Gender Bias in Contextualized Word Embeddings","created":"2019-04-18","cited_by_count":94},{"id":"1606.04316","title":"Time for a change: a tutorial for comparing multiple classifiers through Bayesian analysis","created":"2016-06-14","cited_by_count":93},{"id":"2106.16163","title":"The MultiBERTs: BERT Reproductions for Robustness Analysis","created":"2021-06-30","cited_by_count":92},{"id":"2010.14571","title":"Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus","created":"2020-10-27","cited_by_count":77},{"id":"2106.03765","title":"On Inductive Biases for Heterogeneous Treatment Effect Estimation","created":"2021-06-07","cited_by_count":75},{"id":"2005.00636","title":"We Need to Talk About Random Splits","created":"2020-05-01","cited_by_count":71},{"id":"2106.15195","title":"Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers","created":"2021-06-29","cited_by_count":71},{"id":"2005.14672","title":"Massive Choice, Ample Tasks (MaChAmp): A Toolkit for Multi-task Learning in NLP","created":"2020-05-29","cited_by_count":50},{"id":"1807.01477","title":"Diversity in Machine Learning","created":"2018-07-04","cited_by_count":48},{"id":"2007.04792","title":"Targeting the Benchmark: On Methodology in Current Natural Language Processing Research","created":"2020-07-07","cited_by_count":45},{"id":"2106.01044","title":"Examining the Inductive Bias of Neural Language Models with Artificial Languages","created":"2021-06-02","cited_by_count":40},{"id":"2101.11974","title":"Disembodied Machine Learning: On the Illusion of Objectivity in NLP","created":"2021-01-28","cited_by_count":37},{"id":"2103.07929","title":"A Systematic Review of Reproducibility Research in Natural Language Processing","created":"2021-03-14","cited_by_count":34},{"id":"1709.09500","title":"Replicability Analysis for Natural Language Processing: Testing Significance with Multiple Datasets","created":"2017-09-27","cited_by_count":32},{"id":"2010.03863","title":"What Can We Do to Improve Peer Review in NLP?","created":"2020-10-08","cited_by_count":32},{"id":"1806.04470","title":"Design Challenges and Misconceptions in Neural Sequence Labeling","created":"2018-06-12","cited_by_count":28},{"id":"2109.04282","title":"Cartography Active Learning","created":"2021-09-09","cited_by_count":26},{"id":"2103.06944","title":"Preregistering NLP Research","created":"2021-03-11","cited_by_count":25},{"id":"1512.02167","title":"Simple Baseline for Visual Question Answering","created":"2015-12-07","cited_by_count":24},{"id":"2010.12198","title":"Domain Divergences: a Survey and Empirical Analysis","created":"2020-10-23","cited_by_count":24},{"id":"2012.02260","title":"Deep Learning for Road Traffic Forecasting: Does it Make a Difference?","created":"2020-12-02","cited_by_count":21},{"id":"2105.11301","title":"DaN+: Danish Nested Named Entities and Lexical Normalization","created":"2021-05-24","cited_by_count":19},{"id":"2110.14802","title":"You Are the Best Reviewer of Your Own Papers: An Owner-Assisted Scoring Mechanism","created":"2021-10-27","cited_by_count":19},{"id":"2107.01183","title":"Ethics Sheets for AI Tasks","created":"2021-07-02","cited_by_count":18},{"id":"2009.11654","title":"Best Practices for Managing Data Annotation Projects","created":"2020-09-24","cited_by_count":12},{"id":"1911.03850","title":"Not All Claims are Created Equal: Choosing the Right Statistical Approach to Assess Hypotheses","created":"2019-11-10","cited_by_count":8},{"id":"2204.03829","title":"Does the Market of Citations Reward Reproducible Work?","created":"2022-04-08","cited_by_count":8},{"id":"2104.03026","title":"How to Write a Bias Statement: Recommendations for Submissions to the Workshop on Gender Bias in NLP","created":"2021-04-07","cited_by_count":5},{"id":"2202.11452","title":"Deep Learning Reproducibility and Explainable AI (XAI)","created":"2022-02-23","cited_by_count":4}],"next_cursor":null}