{"list":"other","total":74,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"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":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"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":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"1912.00582","title":"BLiMP: The Benchmark of Linguistic Minimal Pairs for English","created":"2019-12-02","cited_by_count":564},{"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":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"1903.10561","title":"On Measuring Social Biases in Sentence Encoders","created":"2019-03-25","cited_by_count":398},{"id":"1907.13528","title":"What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models","created":"2019-07-31","cited_by_count":320},{"id":"1711.02173","title":"Synthetic and Natural Noise Both Break Neural Machine Translation","created":"2017-11-06","cited_by_count":306},{"id":"1805.01042","title":"Hypothesis Only Baselines in Natural Language Inference","created":"2018-05-02","cited_by_count":295},{"id":"1803.05449","title":"SentEval: An Evaluation Toolkit for Universal Sentence Representations","created":"2018-03-14","cited_by_count":294},{"id":"1611.01603","title":"Bidirectional Attention Flow for Machine Comprehension","created":"2016-11-05","cited_by_count":278},{"id":"2010.05465","title":"COGS: A Compositional Generalization Challenge Based on Semantic Interpretation","created":"2020-10-12","cited_by_count":263},{"id":"1806.08730","title":"The Natural Language Decathlon: Multitask Learning as Question Answering","created":"2018-06-20","cited_by_count":236},{"id":"2012.15761","title":"Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection","created":"2020-12-31","cited_by_count":221},{"id":"2012.15606","title":"HateCheck: Functional Tests for Hate Speech Detection Models","created":"2020-12-31","cited_by_count":216},{"id":"1806.00692","title":"Stress Test Evaluation for Natural Language Inference","created":"2018-06-02","cited_by_count":213},{"id":"1908.06083","title":"Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack","created":"2019-08-17","cited_by_count":176},{"id":"2010.06595","title":"With Little Power Comes Great Responsibility","created":"2020-10-13","cited_by_count":142},{"id":"2008.02637","title":"Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets","created":"2020-08-06","cited_by_count":138},{"id":"1805.02266","title":"Breaking NLI Systems with Sentences that Require Simple Lexical Inferences","created":"2018-05-06","cited_by_count":134},{"id":"2002.00293","title":"Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension","created":"2020-02-02","cited_by_count":131},{"id":"1705.09899","title":"Understanding Abuse: A Typology of Abusive Language Detection Subtasks","created":"2017-05-28","cited_by_count":116},{"id":"2005.00955","title":"How Can We Accelerate Progress Towards Human-like Linguistic Generalization?","created":"2020-05-03","cited_by_count":114},{"id":"1901.05415","title":"Learning from Dialogue after Deployment: Feed Yourself, Chatbot!","created":"2019-01-16","cited_by_count":102},{"id":"1806.09030","title":"On Adversarial Examples for Character-Level Neural Machine Translation","created":"2018-06-23","cited_by_count":85},{"id":"2004.03066","title":"Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition","created":"2020-04-07","cited_by_count":77},{"id":"1805.12282","title":"On the Impact of Various Types of Noise on Neural Machine Translation","created":"2018-05-31","cited_by_count":76},{"id":"2012.15349","title":"DynaSent: A Dynamic Benchmark for Sentiment Analysis","created":"2020-12-30","cited_by_count":63},{"id":"1804.08117","title":"Performance Impact Caused by Hidden Bias of Training Data for Recognizing Textual Entailment","created":"2018-04-22","cited_by_count":59},{"id":"1909.02597","title":"Investigating BERT's Knowledge of Language: Five Analysis Methods with NPIs","created":"2019-09-05","cited_by_count":58},{"id":"1907.04380","title":"Don't Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference","created":"2019-07-09","cited_by_count":49},{"id":"1906.01603","title":"Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study","created":"2019-06-04","cited_by_count":47},{"id":"1808.08609","title":"Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledge","created":"2018-08-26","cited_by_count":46},{"id":"1911.09241","title":"Assessing the Benchmarking Capacity of Machine Reading Comprehension Datasets","created":"2019-11-21","cited_by_count":46},{"id":"1911.03768","title":"The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents","created":"2019-11-09","cited_by_count":45},{"id":"1904.02668","title":"Inoculation by Fine-Tuning: A Method for Analyzing Challenge Datasets","created":"2019-04-04","cited_by_count":42},{"id":"2007.14435","title":"Towards Ecologically Valid Research on Language User Interfaces","created":"2020-07-28","cited_by_count":42},{"id":"2010.03763","title":"Assessing Phrasal Representation and Composition in Transformers","created":"2020-10-08","cited_by_count":41},{"id":"2009.13888","title":"Utility is in the Eye of the User: A Critique of NLP Leaderboards","created":"2020-09-29","cited_by_count":28},{"id":"2010.04762","title":"Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data","created":"2020-10-09","cited_by_count":27},{"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":"1711.01505","title":"Towards Linguistically Generalizable NLP Systems: A Workshop and Shared Task","created":"2017-11-04","cited_by_count":24},{"id":"2004.13606","title":"The Curse of Performance Instability in Analysis Datasets: Consequences, Source, and Suggestions","created":"2020-04-28","cited_by_count":22},{"id":"1910.09302","title":"Diversify Your Datasets: Analyzing Generalization via Controlled Variance in Adversarial Datasets","created":"2019-10-21","cited_by_count":21},{"id":"1910.14254","title":"Harnessing the linguistic signal to predict scalar inferences","created":"2019-10-31","cited_by_count":17},{"id":"1808.06232","title":"Lexicosyntactic Inference in Neural Models","created":"2018-08-19","cited_by_count":14},{"id":"1711.07950","title":"Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent","created":"2017-11-21","cited_by_count":10},{"id":"1909.13851","title":"The Universal Decompositional Semantics Dataset and Decomp Toolkit","created":"2019-09-30","cited_by_count":10},{"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}