{"list":"other","total":123,"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":"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":"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":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"id":"1809.08887","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","created":"2018-09-24","cited_by_count":1139},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"2007.15779","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","created":"2020-07-31","cited_by_count":1009},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"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":"1808.07042","title":"CoQA: A Conversational Question Answering Challenge","created":"2018-08-21","cited_by_count":683},{"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":"1901.04085","title":"Passage Re-ranking with BERT","created":"2019-01-13","cited_by_count":645},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"1508.00305","title":"Compositional Semantic Parsing on Semi-Structured Tables","created":"2015-08-03","cited_by_count":515},{"id":"2010.08191","title":"RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-10-16","cited_by_count":413},{"id":"1509.00685","title":"A Neural Attention Model for Abstractive Sentence Summarization","created":"2015-09-02","cited_by_count":396},{"id":"2004.10645","title":"AmbigQA: Answering Ambiguous Open-domain Questions","created":"2020-04-22","cited_by_count":390},{"id":"1808.07036","title":"QuAC : Question Answering in Context","created":"2018-08-21","cited_by_count":381},{"id":"1801.10198","title":"Generating Wikipedia by Summarizing Long Sequences","created":"2018-01-30","cited_by_count":335},{"id":"2005.00796","title":"A Simple Language Model for Task-Oriented Dialogue","created":"2020-05-02","cited_by_count":332},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"1606.01541","title":"Deep Reinforcement Learning for Dialogue Generation","created":"2016-06-05","cited_by_count":288},{"id":"1611.01603","title":"Bidirectional Attention Flow for Machine Comprehension","created":"2016-11-05","cited_by_count":278},{"id":"2006.14799","title":"Evaluation of Text Generation: A Survey","created":"2020-06-26","cited_by_count":277},{"id":"2010.06467","title":"Pretrained Transformers for Text Ranking: BERT and Beyond","created":"2020-10-13","cited_by_count":267},{"id":"2004.10151","title":"Experience Grounds Language","created":"2020-04-21","cited_by_count":242},{"id":"2005.00181","title":"Sparse, Dense, and Attentional Representations for Text Retrieval","created":"2020-05-01","cited_by_count":214},{"id":"2002.06177","title":"The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence","created":"2020-02-14","cited_by_count":195},{"id":"1909.05378","title":"CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases","created":"2019-09-11","cited_by_count":185},{"id":"1902.00098","title":"The Second Conversational Intelligence Challenge (ConvAI2)","created":"2019-01-31","cited_by_count":179},{"id":"1812.07617","title":"Towards Deep Conversational Recommendations","created":"2018-12-18","cited_by_count":176},{"id":"1809.08267","title":"Neural Approaches to Conversational AI","created":"2018-09-21","cited_by_count":165},{"id":"2010.04898","title":"Open-Domain Question Answering Goes Conversational via Question Rewriting","created":"2020-10-10","cited_by_count":148},{"id":"1906.02285","title":"SParC: Cross-Domain Semantic Parsing in Context","created":"2019-06-05","cited_by_count":144},{"id":"1909.05358","title":"Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset","created":"2019-09-01","cited_by_count":140},{"id":"1508.01745","title":"Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems","created":"2015-08-07","cited_by_count":134},{"id":"1905.13164","title":"Hierarchical Transformers for Multi-Document Summarization","created":"2019-05-30","cited_by_count":132},{"id":"1807.05614","title":"ANN-Benchmarks: A Benchmarking Tool for Approximate Nearest Neighbor Algorithms","created":"2018-07-15","cited_by_count":130},{"id":"2112.08614","title":"KAT: A Knowledge Augmented Transformer for Vision-and-Language","created":"2021-12-16","cited_by_count":126},{"id":"2012.11014","title":"KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA","created":"2020-12-20","cited_by_count":125},{"id":"1805.01788","title":"Equity of Attention: Amortizing Individual Fairness in Rankings","created":"2018-05-04","cited_by_count":124},{"id":"1805.04655","title":"Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information","created":"2018-05-12","cited_by_count":115},{"id":"2109.00590","title":"WebQA: Multihop and Multimodal QA","created":"2021-09-01","cited_by_count":109},{"id":"2005.11364","title":"Open-Retrieval Conversational Question Answering","created":"2020-05-22","cited_by_count":99},{"id":"2002.12328","title":"Few-shot Natural Language Generation for Task-Oriented Dialog","created":"2020-02-27","cited_by_count":89},{"id":"1906.05572","title":"Proactive Human-Machine Conversation with Explicit Conversation Goals","created":"2019-06-13","cited_by_count":88},{"id":"1601.01705","title":"Learning to Compose Neural Networks for Question Answering","created":"2016-01-07","cited_by_count":85},{"id":"1704.00057","title":"Frames: A Corpus for Adding Memory to Goal-Oriented Dialogue Systems","created":"2017-03-31","cited_by_count":85},{"id":"2006.05009","title":"Few-Shot Generative Conversational Query Rewriting","created":"2020-06-09","cited_by_count":85},{"id":"1611.02247","title":"Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic","created":"2016-11-07","cited_by_count":81},{"id":"1511.06481","title":"Variance Reduction in SGD by Distributed Importance Sampling","created":"2015-11-20","cited_by_count":79},{"id":"2010.12834","title":"GO FIGURE: A Meta Evaluation of Factuality in Summarization","created":"2020-10-24","cited_by_count":76},{"id":"1805.05345","title":"Conversations Gone Awry: Detecting Early Signs of Conversational Failure","created":"2018-05-14","cited_by_count":73},{"id":"2105.04166","title":"Few-Shot Conversational Dense Retrieval","created":"2021-05-10","cited_by_count":72},{"id":"2005.05298","title":"SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching","created":"2020-05-11","cited_by_count":71},{"id":"1507.02221","title":"A Hierarchical Recurrent Encoder-Decoder For Generative Context-Aware Query Suggestion","created":"2015-07-08","cited_by_count":68},{"id":"1801.10314","title":"Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph","created":"2018-01-31","cited_by_count":67},{"id":"1905.11553","title":"Target-Guided Open-Domain Conversation","created":"2019-05-28","cited_by_count":66},{"id":"2003.13624","title":"TREC CAsT 2019: The Conversational Assistance Track Overview","created":"2020-03-30","cited_by_count":64},{"id":"1801.03604","title":"Conversational AI: The Science Behind the Alexa Prize","created":"2018-01-11","cited_by_count":63},{"id":"1812.00978","title":"A Survey on Semantic Parsing","created":"2018-12-03","cited_by_count":62},{"id":"1707.02268","title":"Text Summarization Techniques: A Brief Survey","created":"2017-07-07","cited_by_count":59},{"id":"1911.02707","title":"Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs","created":"2019-11-07","cited_by_count":59},{"id":"2009.11352","title":"ConvAI3: Generating Clarifying Questions for Open-Domain Dialogue Systems (ClariQ)","created":"2020-09-23","cited_by_count":58},{"id":"2006.08732","title":"Evaluating Conversational Recommender Systems via User Simulation","created":"2020-06-15","cited_by_count":47},{"id":"1905.12866","title":"Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention","created":"2019-05-30","cited_by_count":44},{"id":"1904.02281","title":"Answer-based Adversarial Training for Generating Clarification Questions","created":"2019-04-04","cited_by_count":43},{"id":"2010.12694","title":"AQuaMuSe: Automatically Generating Datasets for Query-Based Multi-Document Summarization","created":"2020-10-23","cited_by_count":42},{"id":"2101.00178","title":"UnitedQA: A Hybrid Approach for Open Domain Question Answering","created":"2021-01-01","cited_by_count":42},{"id":"1908.00059","title":"GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension","created":"2019-07-31","cited_by_count":41},{"id":"2012.14666","title":"RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems","created":"2020-12-29","cited_by_count":36},{"id":"2006.12442","title":"Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions","created":"2020-06-22","cited_by_count":34},{"id":"1810.06683","title":"FlowQA: Grasping Flow in History for Conversational Machine Comprehension","created":"2018-10-06","cited_by_count":33},{"id":"1812.03593","title":"SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering","created":"2018-12-10","cited_by_count":30},{"id":"1812.10757","title":"Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize","created":"2018-12-27","cited_by_count":29},{"id":"1605.07669","title":"On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems","created":"2016-05-24","cited_by_count":28},{"id":"2003.10555","title":"ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators","created":"2020-03-23","cited_by_count":27},{"id":"1709.06136","title":"Iterative Policy Learning in End-to-End Trainable Task-Oriented Neural Dialog Models","created":"2017-09-18","cited_by_count":26},{"id":"1908.11787","title":"Answering Conversational Questions on Structured Data without Logical Forms","created":"2019-08-30","cited_by_count":24},{"id":"2006.00166","title":"Analyzing and Learning from User Interactions for Search Clarification","created":"2020-05-30","cited_by_count":23},{"id":"1809.10735","title":"A Qualitative Comparison of CoQA, SQuAD 2.0 and QuAC","created":"2018-09-27","cited_by_count":22},{"id":"1908.10731","title":"DeepCopy: Grounded Response Generation with Hierarchical Pointer Networks","created":"2019-08-28","cited_by_count":22},{"id":"2109.04562","title":"TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling","created":"2021-09-09","cited_by_count":22},{"id":"1705.11168","title":"Are distributional representations ready for the real world? Evaluating word vectors for grounded perceptual meaning","created":"2017-05-31","cited_by_count":19},{"id":"1908.05117","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","created":"2019-08-14","cited_by_count":19}],"next_cursor":"100"}