{"list":"other","total":60,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"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":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1911.00536","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","created":"2019-11-01","cited_by_count":842},{"id":"1810.00278","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","created":"2018-09-29","cited_by_count":766},{"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":"1909.02027","title":"An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction","created":"2019-09-04","cited_by_count":386},{"id":"1805.10190","title":"Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces","created":"2018-05-25","cited_by_count":377},{"id":"2005.00796","title":"A Simple Language Model for Task-Oriented Dialogue","created":"2020-05-02","cited_by_count":332},{"id":"1604.04562","title":"A Network-based End-to-End Trainable Task-oriented Dialogue System","created":"2016-04-15","cited_by_count":252},{"id":"1806.08730","title":"The Natural Language Decathlon: Multitask Learning as Question Answering","created":"2018-06-20","cited_by_count":236},{"id":"1905.08743","title":"Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems","created":"2019-05-21","cited_by_count":216},{"id":"1811.01088","title":"Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks","created":"2018-11-02","cited_by_count":215},{"id":"1907.04307","title":"Multilingual Universal Sentence Encoder for Semantic Retrieval","created":"2019-07-09","cited_by_count":193},{"id":"2101.11038","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","created":"2021-01-26","cited_by_count":192},{"id":"1901.08149","title":"TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents","created":"2019-01-23","cited_by_count":188},{"id":"2004.06871","title":"TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue","created":"2020-04-15","cited_by_count":185},{"id":"1910.07931","title":"PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable","created":"2019-10-17","cited_by_count":145},{"id":"1606.03777","title":"Neural Belief Tracker: Data-Driven Dialogue State Tracking","created":"2016-06-12","cited_by_count":143},{"id":"1909.05358","title":"Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset","created":"2019-09-01","cited_by_count":140},{"id":"1705.05414","title":"Key-Value Retrieval Networks for Task-Oriented Dialogue","created":"2017-05-15","cited_by_count":138},{"id":"2005.02877","title":"TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking","created":"2020-05-06","cited_by_count":130},{"id":"2012.03539","title":"UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2","created":"2020-12-07","cited_by_count":111},{"id":"1907.05774","title":"Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems","created":"2019-07-12","cited_by_count":110},{"id":"2009.12005","title":"MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems","created":"2020-09-25","cited_by_count":103},{"id":"1911.10484","title":"Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context","created":"2019-11-24","cited_by_count":99},{"id":"1911.03688","title":"ConveRT: Efficient and Accurate Conversational Representations from Transformers","created":"2019-11-09","cited_by_count":95},{"id":"1704.00057","title":"Frames: A Corpus for Adding Memory to Goal-Oriented Dialogue Systems","created":"2017-03-31","cited_by_count":85},{"id":"1911.03906","title":"Efficient Dialogue State Tracking by Selectively Overwriting Memory","created":"2019-11-10","cited_by_count":76},{"id":"1910.03544","title":"Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking","created":"2019-10-08","cited_by_count":75},{"id":"1907.07421","title":"SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking","created":"2019-07-17","cited_by_count":63},{"id":"1908.01946","title":"Dialog State Tracking: A Neural Reading Comprehension Approach","created":"2019-08-06","cited_by_count":62},{"id":"2108.13740","title":"Plan-then-Generate: Controlled Data-to-Text Generation via Planning","created":"2021-08-31","cited_by_count":52},{"id":"1807.11125","title":"Microsoft Dialogue Challenge: Building End-to-End Task-Completion Dialogue Systems","created":"2018-07-29","cited_by_count":47},{"id":"2009.08115","title":"A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning","created":"2020-09-17","cited_by_count":47},{"id":"1805.09655","title":"Global-Locally Self-Attentive Dialogue State Tracker","created":"2018-05-19","cited_by_count":45},{"id":"2011.09553","title":"A Sequence-to-Sequence Approach to Dialogue State Tracking","created":"2020-11-18","cited_by_count":43},{"id":"1907.10016","title":"Structured Fusion Networks for Dialog","created":"2019-07-23","cited_by_count":40},{"id":"1911.06192","title":"Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering","created":"2019-11-07","cited_by_count":39},{"id":"1911.06394","title":"The Eighth Dialog System Technology Challenge","created":"2019-11-14","cited_by_count":25},{"id":"2103.10518","title":"Pretraining the Noisy Channel Model for Task-Oriented Dialogue","created":"2021-03-18","cited_by_count":23},{"id":"2004.02214","title":"Prototype-to-Style: Dialogue Generation with Style-Aware Editing on Retrieval Memory","created":"2020-04-05","cited_by_count":22},{"id":"1909.00754","title":"Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation","created":"2019-09-02","cited_by_count":21},{"id":"2108.12516","title":"Few-Shot Table-to-Text Generation with Prototype Memory","created":"2021-08-27","cited_by_count":21},{"id":"1909.05528","title":"MOSS: End-to-End Dialog System Framework with Modular Supervision","created":"2019-09-12","cited_by_count":20},{"id":"2006.01554","title":"A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking","created":"2020-06-02","cited_by_count":20},{"id":"2011.08067","title":"Hierarchical Transformer for Task Oriented Dialog Systems","created":"2020-10-24","cited_by_count":14},{"id":"1812.00899","title":"Toward Scalable Neural Dialogue State Tracking Model","created":"2018-12-03","cited_by_count":11},{"id":"1908.02402","title":"Flexibly-Structured Model for Task-Oriented Dialogues","created":"2019-08-06","cited_by_count":10},{"id":"1904.09286","title":"Unifying Question Answering, Text Classification, and Regression via Span Extraction","created":"2019-04-19","cited_by_count":8},{"id":"2107.05168","title":"Dialogue State Tracking with Multi-Level Fusion of Predicted Dialogue States and Conversations","created":"2021-07-12","cited_by_count":6},{"id":"1703.07055","title":"Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems","created":"2017-03-21","cited_by_count":5}],"next_cursor":null}