{"list":"other","total":104,"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"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":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"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":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"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":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"2003.11080","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","created":"2020-03-24","cited_by_count":742},{"id":"2002.08910","title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","created":"2020-02-10","cited_by_count":719},{"id":"1907.09190","title":"ELI5: Long Form Question Answering","created":"2019-07-22","cited_by_count":575},{"id":"2009.02252","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","created":"2020-09-04","cited_by_count":573},{"id":"1911.12237","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","created":"2019-11-27","cited_by_count":535},{"id":"1811.01241","title":"Wizard of Wikipedia: Knowledge-Powered Conversational agents","created":"2018-11-03","cited_by_count":530},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1905.07129","title":"ERNIE: Enhanced Language Representation with Informative Entities","created":"2019-05-17","cited_by_count":528},{"id":"2005.00547","title":"GoEmotions: A Dataset of Fine-Grained Emotions","created":"2020-05-01","cited_by_count":486},{"id":"2005.00700","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","created":"2020-05-02","cited_by_count":476},{"id":"1909.05855","title":"Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset","created":"2019-09-12","cited_by_count":434},{"id":"2003.04807","title":"Efficient Intent Detection with Dual Sentence Encoders","created":"2020-03-10","cited_by_count":433},{"id":"1906.01749","title":"Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model","created":"2019-06-04","cited_by_count":431},{"id":"2010.12421","title":"TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification","created":"2020-10-23","cited_by_count":417},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"1509.00685","title":"A Neural Attention Model for Abstractive Sentence Summarization","created":"2015-09-02","cited_by_count":396},{"id":"1909.02027","title":"An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction","created":"2019-09-04","cited_by_count":386},{"id":"1808.07036","title":"QuAC : Question Answering in Context","created":"2018-08-21","cited_by_count":381},{"id":"2003.06713","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","created":"2020-03-14","cited_by_count":376},{"id":"1808.09121","title":"WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations","created":"2018-08-28","cited_by_count":372},{"id":"1901.11504","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","created":"2019-01-31","cited_by_count":350},{"id":"1711.00489","title":"Don't Decay the Learning Rate, Increase the Batch Size","created":"2017-11-01","cited_by_count":320},{"id":"1908.05739","title":"Abductive Commonsense Reasoning","created":"2019-08-15","cited_by_count":301},{"id":"1909.00277","title":"Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning","created":"2019-08-31","cited_by_count":285},{"id":"1812.06162","title":"An Empirical Model of Large-Batch Training","created":"2018-12-14","cited_by_count":281},{"id":"2004.14373","title":"ToTTo: A Controlled Table-To-Text Generation Dataset","created":"2020-04-29","cited_by_count":268},{"id":"2010.05465","title":"COGS: A Compositional Generalization Challenge Based on Semantic Interpretation","created":"2020-10-12","cited_by_count":263},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239},{"id":"1806.08730","title":"The Natural Language Decathlon: Multitask Learning as Question Answering","created":"2018-06-20","cited_by_count":236},{"id":"2103.08541","title":"Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence","created":"2021-03-15","cited_by_count":225},{"id":"2109.04617","title":"Efficiently Identifying Task Groupings for Multi-Task Learning","created":"2021-09-10","cited_by_count":222},{"id":"1811.01088","title":"Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks","created":"2018-11-02","cited_by_count":215},{"id":"1610.08914","title":"Ex Machina: Personal Attacks Seen at Scale","created":"2016-10-27","cited_by_count":210},{"id":"1912.00741","title":"SemEval-2017 Task 4: Sentiment Analysis in Twitter","created":"2019-12-02","cited_by_count":210},{"id":"1903.08983","title":"SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)","created":"2019-03-19","cited_by_count":207},{"id":"1810.12885","title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension","created":"2018-10-30","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":"2106.10328","title":"Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets","created":"2021-06-18","cited_by_count":181},{"id":"1811.02084","title":"Mesh-TensorFlow: Deep Learning for Supercomputers","created":"2018-11-05","cited_by_count":169},{"id":"2010.05874","title":"Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models","created":"2020-10-12","cited_by_count":169},{"id":"1903.05566","title":"Benchmarking Natural Language Understanding Services for building Conversational Agents","created":"2019-03-13","cited_by_count":166},{"id":"2010.03093","title":"WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization","created":"2020-10-07","cited_by_count":154},{"id":"2002.03932","title":"Pre-training Tasks for Embedding-based Large-scale Retrieval","created":"2020-02-10","cited_by_count":153},{"id":"2007.02871","title":"DART: Open-Domain Structured Data Record to Text Generation","created":"2020-07-06","cited_by_count":145},{"id":"1905.12688","title":"Choosing Transfer Languages for Cross-Lingual Learning","created":"2019-05-29","cited_by_count":144},{"id":"2005.00770","title":"Exploring and Predicting Transferability across NLP Tasks","created":"2020-05-02","cited_by_count":128},{"id":"2005.02324","title":"Neural CRF Model for Sentence Alignment in Text Simplification","created":"2020-05-05","cited_by_count":106},{"id":"2109.10686","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","created":"2021-09-22","cited_by_count":106},{"id":"2011.04946","title":"When Do You Need Billions of Words of Pretraining Data?","created":"2020-11-10","cited_by_count":104},{"id":"1810.07942","title":"Semantic Parsing for Task Oriented Dialog using Hierarchical Representations","created":"2018-10-18","cited_by_count":101},{"id":"2103.13009","title":"UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark","created":"2021-03-24","cited_by_count":98},{"id":"2009.13570","title":"DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue","created":"2020-09-28","cited_by_count":89},{"id":"2106.09449","title":"DocNLI: A Large-scale Dataset for Document-level Natural Language Inference","created":"2021-06-17","cited_by_count":75},{"id":"1909.02197","title":"Investigating Multilingual NMT Representations at Scale","created":"2019-09-05","cited_by_count":68},{"id":"1707.05246","title":"Learning to select data for transfer learning with Bayesian Optimization","created":"2017-07-17","cited_by_count":64},{"id":"1911.03905","title":"Semantic Noise Matters for Neural Natural Language Generation","created":"2019-11-10","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":"1702.08303","title":"Identifying beneficial task relations for multi-task learning in deep neural networks","created":"2017-02-27","cited_by_count":59},{"id":"1906.03497","title":"This Email Could Save Your Life: Introducing the Task of Email Subject Line Generation","created":"2019-06-08","cited_by_count":58},{"id":"1707.01161","title":"Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Models","created":"2017-07-04","cited_by_count":57},{"id":"1907.06292","title":"TWEETQA: A Social Media Focused Question Answering Dataset","created":"2019-07-14","cited_by_count":55},{"id":"2104.07478","title":"Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations","created":"2021-04-15","cited_by_count":55},{"id":"1811.06031","title":"A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks","created":"2018-11-14","cited_by_count":54},{"id":"2104.05196","title":"StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer","created":"2021-04-12","cited_by_count":34},{"id":"2102.09094","title":"Quiz-Style Question Generation for News Stories","created":"2021-02-18","cited_by_count":23},{"id":"1904.04153","title":"AutoSeM: Automatic Task Selection and Mixing in Multi-Task Learning","created":"2019-04-08","cited_by_count":22},{"id":"2106.08190","title":"Question Answering Infused Pre-training of General-Purpose Contextualized Representations","created":"2021-06-15","cited_by_count":19}],"next_cursor":"100"}