{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"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":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"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":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"2009.06367","title":"GeDi: Generative Discriminator Guided Sequence Generation","created":"2020-09-14","cited_by_count":378},{"id":"1705.04304","title":"A Deep Reinforced Model for Abstractive Summarization","created":"2017-05-11","cited_by_count":365},{"id":"1909.00161","title":"Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach","created":"2019-08-31","cited_by_count":308},{"id":"1606.01541","title":"Deep Reinforcement Learning for Dialogue Generation","created":"2016-06-05","cited_by_count":288},{"id":"1703.00955","title":"Toward Controlled Generation of Text","created":"2017-03-02","cited_by_count":272},{"id":"1706.09254","title":"The E2E Dataset: New Challenges For End-to-End Generation","created":"2017-06-28","cited_by_count":253},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239},{"id":"1702.08892","title":"Bridging the Gap Between Value and Policy Based Reinforcement Learning","created":"2017-02-28","cited_by_count":182},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176},{"id":"1704.06440","title":"Equivalence Between Policy Gradients and Soft Q-Learning","created":"2017-04-21","cited_by_count":173},{"id":"1607.07086","title":"An Actor-Critic Algorithm for Sequence Prediction","created":"2016-07-24","cited_by_count":159},{"id":"1805.11080","title":"Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting","created":"2018-05-28","cited_by_count":158},{"id":"1512.08562","title":"Taming the Noise in Reinforcement Learning via Soft Updates","created":"2015-12-28","cited_by_count":127},{"id":"1904.02792","title":"Unifying Human and Statistical Evaluation for Natural Language Generation","created":"2019-04-04","cited_by_count":127},{"id":"2005.00268","title":"Towards Controllable Biases in Language Generation","created":"2020-05-01","cited_by_count":112},{"id":"1611.02796","title":"Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control","created":"2016-11-09","cited_by_count":101},{"id":"1709.08624","title":"Long Text Generation via Adversarial Training with Leaked Information","created":"2017-09-24","cited_by_count":100},{"id":"1811.02549","title":"Language GANs Falling Short","created":"2018-11-06","cited_by_count":97},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93},{"id":"1907.01752","title":"On the Weaknesses of Reinforcement Learning for Neural Machine Translation","created":"2019-07-03","cited_by_count":82},{"id":"1609.00150","title":"Reward Augmented Maximum Likelihood for Neural Structured Prediction","created":"2016-09-01","cited_by_count":81},{"id":"1808.08866","title":"A Study of Reinforcement Learning for Neural Machine Translation","created":"2018-08-27","cited_by_count":74},{"id":"1804.06451","title":"Multi-Reward Reinforced Summarization with Saliency and Entailment","created":"2018-04-17","cited_by_count":73},{"id":"1506.08941","title":"Language Understanding for Text-based Games Using Deep Reinforcement Learning","created":"2015-06-30","cited_by_count":71},{"id":"2009.07839","title":"Text Generation by Learning from Demonstrations","created":"2020-09-16","cited_by_count":64},{"id":"2012.02952","title":"Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation","created":"2020-12-05","cited_by_count":47},{"id":"1804.11258","title":"Toward Diverse Text Generation with Inverse Reinforcement Learning","created":"2018-04-30","cited_by_count":41},{"id":"1707.01891","title":"Trust-PCL: An Off-Policy Trust Region Method for Continuous Control","created":"2017-07-06","cited_by_count":30},{"id":"2009.08205","title":"Generating Label Cohesive and Well-Formed Adversarial Claims","created":"2020-09-17","cited_by_count":27},{"id":"1712.02838","title":"End-to-End Offline Goal-Oriented Dialog Policy Learning via Policy Gradient","created":"2017-12-07","cited_by_count":23},{"id":"1704.07489","title":"Multi-Task Video Captioning with Video and Entailment Generation","created":"2017-04-24","cited_by_count":17},{"id":"1809.00794","title":"Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation","created":"2018-09-04","cited_by_count":13},{"id":"1702.03334","title":"Batch Policy Gradient Methods for Improving Neural Conversation Models","created":"2017-02-10","cited_by_count":10},{"id":"1510.09202","title":"Generating Text with Deep Reinforcement Learning","created":"2015-10-30","cited_by_count":4}],"next_cursor":null}