{"list":"other","total":64,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"1708.06131","title":"Evasion Attacks against Machine Learning at Test Time","created":"2017-08-21","cited_by_count":689},{"id":"2007.12626","title":"SummEval: Re-evaluating Summarization Evaluation","created":"2020-07-24","cited_by_count":674},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"1804.06876","title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","created":"2018-04-18","cited_by_count":659},{"id":"1905.07697","title":"Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations","created":"2019-05-19","cited_by_count":614},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"id":"1804.09301","title":"Gender Bias in Coreference Resolution","created":"2018-04-25","cited_by_count":442},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"1901.09960","title":"Using Pre-Training Can Improve Model Robustness and Uncertainty","created":"2019-01-28","cited_by_count":373},{"id":"1711.10160","title":"Snorkel: Rapid Training Data Creation with Weak Supervision","created":"2017-11-28","cited_by_count":372},{"id":"2004.01970","title":"BAE: BERT-based Adversarial Examples for Text Classification","created":"2020-04-04","cited_by_count":316},{"id":"1711.02173","title":"Synthetic and Natural Noise Both Break Neural Machine Translation","created":"2017-11-06","cited_by_count":306},{"id":"1804.11283","title":"Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies","created":"2018-04-30","cited_by_count":294},{"id":"1909.09223","title":"InterpretML: A Unified Framework for Machine Learning Interpretability","created":"2019-09-19","cited_by_count":246},{"id":"1806.00692","title":"Stress Test Evaluation for Natural Language Inference","created":"2018-06-02","cited_by_count":213},{"id":"1907.04135","title":"The What-If Tool: Interactive Probing of Machine Learning Models","created":"2019-07-09","cited_by_count":207},{"id":"1908.08960","title":"Neural Text Summarization: A Critical Evaluation","created":"2019-08-23","cited_by_count":189},{"id":"1909.03012","title":"One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques","created":"2019-09-06","cited_by_count":164},{"id":"1805.02266","title":"Breaking NLI Systems with Sentences that Require Simple Lexical Inferences","created":"2018-05-06","cited_by_count":134},{"id":"2008.05122","title":"The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models","created":"2020-08-12","cited_by_count":125},{"id":"2004.14444","title":"The Effect of Natural Distribution Shift on Question Answering Models","created":"2020-04-29","cited_by_count":104},{"id":"1904.05419","title":"FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning","created":"2019-04-10","cited_by_count":93},{"id":"2009.09191","title":"OpenAttack: An Open-source Textual Adversarial Attack Toolkit","created":"2020-09-19","cited_by_count":84},{"id":"2004.03066","title":"Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition","created":"2020-04-07","cited_by_count":77},{"id":"1909.09251","title":"AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models","created":"2019-09-19","cited_by_count":74},{"id":"1810.12343","title":"Content Selection in Deep Learning Models of Summarization","created":"2018-10-29","cited_by_count":64},{"id":"2006.01969","title":"REL: An Entity Linker Standing on the Shoulders of Giants","created":"2020-06-02","cited_by_count":61},{"id":"1908.00176","title":"FairSight: Visual Analytics for Fairness in Decision Making","created":"2019-08-01","cited_by_count":59},{"id":"1808.00196","title":"Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Models","created":"2018-08-01","cited_by_count":50},{"id":"1809.09672","title":"BanditSum: Extractive Summarization as a Contextual Bandit","created":"2018-09-25","cited_by_count":46},{"id":"2005.05909","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","created":"2020-04-29","cited_by_count":45},{"id":"1901.03735","title":"EQUATE: A Benchmark Evaluation Framework for Quantitative Reasoning in Natural Language Inference","created":"2019-01-11","cited_by_count":39},{"id":"1902.00863","title":"Neural Extractive Text Summarization with Syntactic Compression","created":"2019-02-03","cited_by_count":37},{"id":"2004.14839","title":"Do Neural Models Learn Systematicity of Monotonicity Inference in Natural Language?","created":"2020-04-30","cited_by_count":29},{"id":"1908.11723","title":"Earlier Isn't Always Better: Sub-aspect Analysis on Corpus and System Biases in Summarization","created":"2019-08-30","cited_by_count":28},{"id":"2010.10418","title":"ConjNLI: Natural Language Inference Over Conjunctive Sentences","created":"2020-10-20","cited_by_count":27},{"id":"1811.07033","title":"Analyzing Compositionality-Sensitivity of NLI Models","created":"2018-11-16","cited_by_count":26},{"id":"2004.02709","title":"Evaluating Models' Local Decision Boundaries via Contrast Sets","created":"2020-04-06","cited_by_count":24},{"id":"2010.10363","title":"Bootleg: Chasing the Tail with Self-Supervised Named Entity Disambiguation","created":"2020-10-20","cited_by_count":24},{"id":"1909.06349","title":"Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices","created":"2019-09-13","cited_by_count":23},{"id":"1805.04212","title":"Behavior Analysis of NLI Models: Uncovering the Influence of Three Factors on Robustness","created":"2018-05-11","cited_by_count":17},{"id":"2005.14253","title":"Empirical Evaluation of Pretraining Strategies for Supervised Entity Linking","created":"2020-05-28","cited_by_count":17},{"id":"1710.02925","title":"Natural Language Inference from Multiple Premises","created":"2017-10-09","cited_by_count":13},{"id":"1906.01393","title":"SherLIiC: A Typed Event-Focused Lexical Inference Benchmark for Evaluating Natural Language Inference","created":"2019-06-04","cited_by_count":8},{"id":"2004.07993","title":"CrossCheck: Rapid, Reproducible, and Interpretable Model Evaluation","created":"2020-04-16","cited_by_count":7},{"id":"1810.13033","title":"Stress-Testing Neural Models of Natural Language Inference with Multiply-Quantified Sentences","created":"2018-10-30","cited_by_count":6}],"next_cursor":null}