{"list":"other","total":62,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"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":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"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":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"1904.01130","title":"PAWS: Paraphrase Adversaries from Word Scrambling","created":"2019-04-01","cited_by_count":402},{"id":"1911.03894","title":"CamemBERT: a Tasty French Language Model","created":"2019-11-10","cited_by_count":368},{"id":"1808.05326","title":"SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference","created":"2018-08-16","cited_by_count":333},{"id":"2004.12993","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","created":"2020-04-27","cited_by_count":332},{"id":"1312.3005","title":"One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling","created":"2013-12-11","cited_by_count":308},{"id":"1805.01042","title":"Hypothesis Only Baselines in Natural Language Inference","created":"2018-05-02","cited_by_count":295},{"id":"2004.06100","title":"Pretrained Transformers Improve Out-of-Distribution Robustness","created":"2020-04-13","cited_by_count":294},{"id":"1605.07725","title":"Adversarial Training Methods for Semi-Supervised Text Classification","created":"2016-05-25","cited_by_count":280},{"id":"1909.03683","title":"Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases","created":"2019-09-09","cited_by_count":280},{"id":"1910.11476","title":"A Unified MRC Framework for Named Entity Recognition","created":"2019-10-25","cited_by_count":199},{"id":"1908.07898","title":"Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets","created":"2019-08-21","cited_by_count":175},{"id":"2002.04108","title":"Adversarial Filters of Dataset Biases","created":"2020-02-10","cited_by_count":160},{"id":"1912.05372","title":"FlauBERT: Unsupervised Language Model Pre-training for French","created":"2019-12-11","cited_by_count":153},{"id":"2005.07150","title":"Named Entity Recognition as Dependency Parsing","created":"2020-05-14","cited_by_count":151},{"id":"2010.10906","title":"German's Next Language Model","created":"2020-10-21","cited_by_count":144},{"id":"1908.05267","title":"Towards Debiasing Fact Verification Models","created":"2019-08-14","cited_by_count":143},{"id":"1912.11078","title":"Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview","created":"2019-11-09","cited_by_count":137},{"id":"1909.06321","title":"End-to-End Bias Mitigation by Modelling Biases in Corpora","created":"2019-09-13","cited_by_count":128},{"id":"1908.10763","title":"Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual","created":"2019-08-28","cited_by_count":119},{"id":"1912.07076","title":"Multilingual is not enough: BERT for Finnish","created":"2019-12-15","cited_by_count":119},{"id":"2009.12303","title":"Towards Debiasing NLU Models from Unknown Biases","created":"2020-09-25","cited_by_count":116},{"id":"1912.09582","title":"BERTje: A Dutch BERT Model","created":"2019-12-19","cited_by_count":109},{"id":"1906.02443","title":"Robust Neural Machine Translation with Doubly Adversarial Inputs","created":"2019-06-06","cited_by_count":106},{"id":"1608.08967","title":"Robustness of classifiers: from adversarial to random noise","created":"2016-08-31","cited_by_count":88},{"id":"2001.06286","title":"RobBERT: a Dutch RoBERTa-based Language Model","created":"2020-01-17","cited_by_count":88},{"id":"2004.11999","title":"Syntactic Data Augmentation Increases Robustness to Inference Heuristics","created":"2020-04-24","cited_by_count":86},{"id":"2005.00315","title":"Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance","created":"2020-05-01","cited_by_count":85},{"id":"2012.01300","title":"Learning from others' mistakes: Avoiding dataset biases without modeling them","created":"2020-12-02","cited_by_count":83},{"id":"2010.11683","title":"An Analysis of Simple Data Augmentation for Named Entity Recognition","created":"2020-10-22","cited_by_count":76},{"id":"2011.03856","title":"Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles","created":"2020-11-07","cited_by_count":43},{"id":"1802.04302","title":"Evaluating Compositionality in Sentence Embeddings","created":"2018-02-12","cited_by_count":35},{"id":"1410.3791","title":"POLYGLOT-NER: Massive Multilingual Named Entity Recognition","created":"2014-10-14","cited_by_count":32},{"id":"1808.06876","title":"Adversarial training for multi-context joint entity and relation extraction","created":"2018-08-21","cited_by_count":29},{"id":"1907.04389","title":"On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference","created":"2019-07-09","cited_by_count":29},{"id":"1701.02877","title":"Generalisation in Named Entity Recognition: A Quantitative Analysis","created":"2017-01-11","cited_by_count":25},{"id":"2006.07890","title":"FinEst BERT and CroSloEngual BERT: less is more in multilingual models","created":"2020-06-14","cited_by_count":20},{"id":"2007.06897","title":"What's in a Name? Are BERT Named Entity Representations just as Good for any other Name?","created":"2020-07-14","cited_by_count":17},{"id":"2004.04564","title":"Interpretability Analysis for Named Entity Recognition to Understand System Predictions and How They Can Improve","created":"2020-04-09","cited_by_count":16},{"id":"1903.11222","title":"ner and pos when nothing is capitalized","created":"2019-03-27","cited_by_count":15},{"id":"2004.04123","title":"Entity-Switched Datasets: An Approach to Auditing the In-Domain Robustness of Named Entity Recognition Models","created":"2020-04-08","cited_by_count":13},{"id":"1912.07095","title":"Robust Named Entity Recognition with Truecasing Pretraining","created":"2019-12-15","cited_by_count":11},{"id":"2010.12510","title":"Improving Robustness by Augmenting Training Sentences with Predicate-Argument Structures","created":"2020-10-23","cited_by_count":10},{"id":"1911.03861","title":"Increasing Robustness to Spurious Correlations using Forgettable Examples","created":"2019-11-10","cited_by_count":7},{"id":"2004.12126","title":"A Rigorous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land?","created":"2020-04-25","cited_by_count":6},{"id":"2003.10296","title":"Adaptive Name Entity Recognition under Highly Unbalanced Data","created":"2020-03-10","cited_by_count":4},{"id":"2011.01549","title":"DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks","created":"2020-11-03","cited_by_count":4},{"id":"2102.09928","title":"Do End-to-End Speech Recognition Models Care About Context?","created":"2021-02-17","cited_by_count":3}],"next_cursor":null}