{"list":"other","total":58,"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"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":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1610.02242","title":"Temporal Ensembling for Semi-Supervised Learning","created":"2016-10-07","cited_by_count":1057},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"1704.03976","title":"Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning","created":"2017-04-13","cited_by_count":920},{"id":"1506.03134","title":"Pointer Networks","created":"2015-06-09","cited_by_count":895},{"id":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"1704.00051","title":"Reading Wikipedia to Answer Open-Domain Questions","created":"2017-03-31","cited_by_count":777},{"id":"1511.04508","title":"Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks","created":"2015-11-14","cited_by_count":678},{"id":"1907.11932","title":"Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment","created":"2019-07-27","cited_by_count":671},{"id":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"2009.00236","title":"A Survey of Deep Active Learning","created":"2020-08-30","cited_by_count":554},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"id":"2004.09984","title":"BERT-ATTACK: Adversarial Attack Against BERT Using BERT","created":"2020-04-21","cited_by_count":491},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"1611.09830","title":"NewsQA: A Machine Comprehension Dataset","created":"2016-11-29","cited_by_count":331},{"id":"1710.09282","title":"A Survey of Model Compression and Acceleration for Deep Neural Networks","created":"2017-10-23","cited_by_count":301},{"id":"1611.01603","title":"Bidirectional Attention Flow for Machine Comprehension","created":"2016-11-05","cited_by_count":278},{"id":"2012.15828","title":"MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers","created":"2020-12-31","cited_by_count":245},{"id":"1804.09541","title":"QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension","created":"2018-04-23","cited_by_count":164},{"id":"1707.05928","title":"Deep Active Learning for Named Entity Recognition","created":"2017-07-19","cited_by_count":108},{"id":"1907.04829","title":"BAM! Born-Again Multi-Task Networks for Natural Language Understanding","created":"2019-07-10","cited_by_count":85},{"id":"1908.01851","title":"Self-Knowledge Distillation in Natural Language Processing","created":"2019-08-02","cited_by_count":60},{"id":"1906.04980","title":"Unsupervised Question Answering by Cloze Translation","created":"2019-06-12","cited_by_count":59},{"id":"1910.08381","title":"Model Compression with Two-stage Multi-teacher Knowledge Distillation for Web Question Answering System","created":"2019-10-18","cited_by_count":43},{"id":"1904.09482","title":"Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding","created":"2019-04-20","cited_by_count":37},{"id":"1906.08042","title":"Low-resource Deep Entity Resolution with Transfer and Active Learning","created":"2019-06-17","cited_by_count":37},{"id":"2005.01525","title":"To Test Machine Comprehension, Start by Defining Comprehension","created":"2020-05-04","cited_by_count":31},{"id":"2105.14553","title":"Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrifice","created":"2021-05-30","cited_by_count":30},{"id":"1702.02206","title":"Semi-Supervised QA with Generative Domain-Adaptive Nets","created":"2017-02-07","cited_by_count":27},{"id":"1805.08092","title":"Efficient and Robust Question Answering from Minimal Context over Documents","created":"2018-05-21","cited_by_count":26},{"id":"1711.05345","title":"Supervised and Unsupervised Transfer Learning for Question Answering","created":"2017-11-14","cited_by_count":24},{"id":"2104.05062","title":"Achieving Model Robustness through Discrete Adversarial Training","created":"2021-04-11","cited_by_count":23},{"id":"1804.00720","title":"Simple and Effective Semi-Supervised Question Answering","created":"2018-04-02","cited_by_count":22},{"id":"1609.05284","title":"ReasoNet: Learning to Stop Reading in Machine Comprehension","created":"2016-09-17","cited_by_count":21},{"id":"2012.15495","title":"Towards Zero-Shot Knowledge Distillation for Natural Language Processing","created":"2020-12-31","cited_by_count":20},{"id":"1808.07644","title":"Attention-Guided Answer Distillation for Machine Reading Comprehension","created":"2018-08-23","cited_by_count":18},{"id":"1809.04913","title":"Query-Efficient Black-Box Attack by Active Learning","created":"2018-09-13","cited_by_count":15},{"id":"2011.08908","title":"SHIELD: Defending Textual Neural Networks against Multiple Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher","created":"2020-11-17","cited_by_count":13},{"id":"2004.13671","title":"Active Learning for Coreference Resolution using Discrete Annotation","created":"2020-04-28","cited_by_count":12},{"id":"2001.02524","title":"LTP: A New Active Learning Strategy for CRF-Based Named Entity Recognition","created":"2020-01-08","cited_by_count":10},{"id":"1702.02171","title":"Question Answering through Transfer Learning from Large Fine-grained Supervision Data","created":"2017-02-07","cited_by_count":9},{"id":"1904.09636","title":"Model Compression with Multi-Task Knowledge Distillation for Web-scale Question Answering System","created":"2019-04-21","cited_by_count":5},{"id":"1610.09996","title":"End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension","created":"2016-10-31","cited_by_count":4},{"id":"1808.00496","title":"SlimNets: An Exploration of Deep Model Compression and Acceleration","created":"2018-08-01","cited_by_count":4},{"id":"1907.01686","title":"Machine Reading Comprehension: a Literature Review","created":"2019-06-30","cited_by_count":4},{"id":"1401.6427","title":"Towards Unsupervised Learning of Temporal Relations between Events","created":"2014-01-23","cited_by_count":1}],"next_cursor":null}