{"list":"other","total":57,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"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":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1805.01070","title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties","created":"2018-05-03","cited_by_count":457},{"id":"2101.11718","title":"BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation","created":"2021-01-27","cited_by_count":412},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"1901.09451","title":"Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting","created":"2019-01-27","cited_by_count":349},{"id":"1906.08976","title":"Mitigating Gender Bias in Natural Language Processing: Literature Review","created":"2019-06-21","cited_by_count":287},{"id":"1812.08951","title":"Analysis Methods in Neural Language Processing: A Survey","created":"2018-12-21","cited_by_count":277},{"id":"1805.04508","title":"Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems","created":"2018-05-11","cited_by_count":234},{"id":"1608.04207","title":"Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks","created":"2016-08-15","cited_by_count":216},{"id":"1806.00692","title":"Stress Test Evaluation for Natural Language Inference","created":"2018-06-02","cited_by_count":213},{"id":"1807.11714","title":"Gender Bias in Neural Natural Language Processing","created":"2018-07-31","cited_by_count":211},{"id":"1910.11476","title":"A Unified MRC Framework for Named Entity Recognition","created":"2019-10-25","cited_by_count":199},{"id":"1911.02855","title":"Dice Loss for Data-imbalanced NLP Tasks","created":"2019-11-07","cited_by_count":182},{"id":"1707.00075","title":"Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations","created":"2017-07-01","cited_by_count":165},{"id":"2203.16804","title":"BRIO: Bringing Order to Abstractive Summarization","created":"2022-03-31","cited_by_count":161},{"id":"1808.07231","title":"Reducing Gender Bias in Abusive Language Detection","created":"2018-08-22","cited_by_count":152},{"id":"1809.10610","title":"Counterfactual Fairness in Text Classification through Robustness","created":"2018-09-27","cited_by_count":151},{"id":"1909.00871","title":"It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution","created":"2019-09-02","cited_by_count":103},{"id":"2110.08527","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","created":"2021-10-16","cited_by_count":97},{"id":"2005.02439","title":"Contextualizing Hate Speech Classifiers with Post-hoc Explanation","created":"2020-05-05","cited_by_count":84},{"id":"1909.02074","title":"Jointly Learning to Align and Translate with Transformer Models","created":"2019-09-04","cited_by_count":75},{"id":"2203.09192","title":"Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists","created":"2022-03-17","cited_by_count":55},{"id":"2004.14243","title":"Towards Transparent and Explainable Attention Models","created":"2020-04-29","cited_by_count":47},{"id":"2004.14088","title":"Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting","created":"2020-04-29","cited_by_count":41},{"id":"1612.04629","title":"How Grammatical is Character-level Neural Machine Translation? Assessing MT Quality with Contrastive Translation Pairs","created":"2016-12-14","cited_by_count":39},{"id":"1704.07431","title":"A Challenge Set Approach to Evaluating Machine Translation","created":"2017-04-24","cited_by_count":37},{"id":"2210.14975","title":"MABEL: Attenuating Gender Bias using Textual Entailment Data","created":"2022-10-26","cited_by_count":31},{"id":"2006.08564","title":"Intra-Processing Methods for Debiasing Neural Networks","created":"2020-06-15","cited_by_count":27},{"id":"2012.15150","title":"Improving BERT with Syntax-aware Local Attention","created":"2020-12-30","cited_by_count":26},{"id":"2203.10741","title":"HIBRIDS: Attention with Hierarchical Biases for Structure-aware Long Document Summarization","created":"2022-03-21","cited_by_count":23},{"id":"2105.06977","title":"Do Context-Aware Translation Models Pay the Right Attention?","created":"2021-05-14","cited_by_count":21},{"id":"2211.11109","title":"Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness","created":"2022-11-20","cited_by_count":21},{"id":"2106.03441","title":"Attention Temperature Matters in Abstractive Summarization Distillation","created":"2021-06-07","cited_by_count":14},{"id":"2101.00371","title":"On-the-Fly Attention Modulation for Neural Generation","created":"2021-01-02","cited_by_count":12},{"id":"2104.02205","title":"Attention Head Masking for Inference Time Content Selection in Abstractive Summarization","created":"2021-04-06","cited_by_count":9},{"id":"1910.00139","title":"Interrogating the Explanatory Power of Attention in Neural Machine Translation","created":"2019-09-30","cited_by_count":7},{"id":"2010.04606","title":"Mark-Evaluate: Assessing Language Generation using Population Estimation Methods","created":"2020-10-09","cited_by_count":5}],"next_cursor":null}