{"list":"other","total":51,"rows":[{"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":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"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":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"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":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"2005.00700","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","created":"2020-05-02","cited_by_count":476},{"id":"1706.04115","title":"Zero-Shot Relation Extraction via Reading Comprehension","created":"2017-06-13","cited_by_count":426},{"id":"1904.01130","title":"PAWS: Paraphrase Adversaries from Word Scrambling","created":"2019-04-01","cited_by_count":402},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344},{"id":"1611.09830","title":"NewsQA: A Machine Comprehension Dataset","created":"2016-11-29","cited_by_count":331},{"id":"1806.08730","title":"The Natural Language Decathlon: Multitask Learning as Question Answering","created":"2018-06-20","cited_by_count":236},{"id":"1704.05179","title":"SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine","created":"2017-04-18","cited_by_count":225},{"id":"1811.01088","title":"Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks","created":"2018-11-02","cited_by_count":215},{"id":"2102.07033","title":"PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them","created":"2021-02-13","cited_by_count":200},{"id":"2101.11038","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","created":"2021-01-26","cited_by_count":192},{"id":"1705.00106","title":"Learning to Ask: Neural Question Generation for Reading Comprehension","created":"2017-04-29","cited_by_count":186},{"id":"1910.09753","title":"MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension","created":"2019-10-22","cited_by_count":184},{"id":"2002.11361","title":"Understanding Self-Training for Gradual Domain Adaptation","created":"2020-02-26","cited_by_count":149},{"id":"1906.05416","title":"Synthetic QA Corpora Generation with Roundtrip Consistency","created":"2019-06-12","cited_by_count":143},{"id":"2010.08240","title":"Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks","created":"2020-10-16","cited_by_count":138},{"id":"2005.00628","title":"Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?","created":"2020-05-01","cited_by_count":127},{"id":"2002.09599","title":"Training Question Answering Models From Synthetic Data","created":"2020-02-22","cited_by_count":95},{"id":"2012.12624","title":"Learning Dense Representations of Phrases at Scale","created":"2020-12-23","cited_by_count":91},{"id":"2104.08678","title":"Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation","created":"2021-04-18","cited_by_count":79},{"id":"1804.07927","title":"DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension","created":"2018-04-21","cited_by_count":71},{"id":"1805.06627","title":"Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures","created":"2018-05-17","cited_by_count":64},{"id":"1906.05807","title":"Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index","created":"2019-06-13","cited_by_count":64},{"id":"2101.00438","title":"Few-Shot Question Answering by Pretraining Span Selection","created":"2021-01-02","cited_by_count":62},{"id":"1906.04980","title":"Unsupervised Question Answering by Cloze Translation","created":"2019-06-12","cited_by_count":59},{"id":"1804.11147","title":"FIRST: A Framework for Optimizing Information Quality in Mobile Crowdsensing Systems","created":"2018-04-30","cited_by_count":50},{"id":"1805.05942","title":"Harvesting Paragraph-Level Question-Answer Pairs from Wikipedia","created":"2018-05-15","cited_by_count":49},{"id":"2012.14978","title":"Few-Shot Named Entity Recognition: A Comprehensive Study","created":"2020-12-29","cited_by_count":41},{"id":"1909.11291","title":"Question Answering is a Format; When is it Useful?","created":"2019-09-25","cited_by_count":25},{"id":"1804.07726","title":"Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehension","created":"2018-04-20","cited_by_count":23},{"id":"1711.05885","title":"Crowdsourcing Question-Answer Meaning Representations","created":"2017-11-16","cited_by_count":21},{"id":"1911.02896","title":"Contextualized Sparse Representations for Real-Time Open-Domain Question Answering","created":"2019-11-07","cited_by_count":11},{"id":"2010.05103","title":"On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks","created":"2020-10-10","cited_by_count":11},{"id":"2004.14287","title":"General Purpose Text Embeddings from Pre-trained Language Models for Scalable Inference","created":"2020-04-29","cited_by_count":9}],"next_cursor":null}