{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"1511.06349","title":"Generating Sentences from a Continuous Space","created":"2015-11-19","cited_by_count":612},{"id":"1802.01886","title":"Texygen: A Benchmarking Platform for Text Generation Models","created":"2018-02-06","cited_by_count":491},{"id":"1711.00043","title":"Unsupervised Machine Translation Using Monolingual Corpora Only","created":"2017-10-31","cited_by_count":273},{"id":"2004.14373","title":"ToTTo: A Controlled Table-To-Text Generation Dataset","created":"2020-04-29","cited_by_count":268},{"id":"2004.07347","title":"HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data","created":"2020-04-15","cited_by_count":264},{"id":"1803.09017","title":"Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis","created":"2018-03-23","cited_by_count":259},{"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":"2006.12013","title":"CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information","created":"2020-06-22","cited_by_count":235},{"id":"2201.05966","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","created":"2022-01-16","cited_by_count":231},{"id":"1707.08052","title":"Challenges in Data-to-Document Generation","created":"2017-07-25","cited_by_count":226},{"id":"1903.10145","title":"Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing","created":"2019-03-25","cited_by_count":191},{"id":"2101.05779","title":"Structured Prediction as Translation between Augmented Natural Languages","created":"2021-01-14","cited_by_count":183},{"id":"2104.00369","title":"FeTaQA: Free-form Table Question Answering","created":"2021-04-01","cited_by_count":175},{"id":"1710.11041","title":"Unsupervised Neural Machine Translation","created":"2017-10-30","cited_by_count":149},{"id":"1611.00179","title":"Dual Learning for Machine Translation","created":"2016-11-01","cited_by_count":148},{"id":"2007.02871","title":"DART: Open-Domain Structured Data Record to Text Generation","created":"2020-07-06","cited_by_count":145},{"id":"1706.02262","title":"InfoVAE: Information Maximizing Variational Autoencoders","created":"2017-06-07","cited_by_count":124},{"id":"2007.08426","title":"Investigating Pretrained Language Models for Graph-to-Text Generation","created":"2020-07-16","cited_by_count":117},{"id":"2004.04092","title":"Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space","created":"2020-04-05","cited_by_count":114},{"id":"1809.00582","title":"Data-to-Text Generation with Content Selection and Planning","created":"2018-09-03","cited_by_count":106},{"id":"2005.10433","title":"Text-to-Text Pre-Training for Data-to-Text Tasks","created":"2020-05-21","cited_by_count":104},{"id":"1904.03396","title":"Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation","created":"2019-04-06","cited_by_count":75},{"id":"1911.03905","title":"Semantic Noise Matters for Neural Natural Language Generation","created":"2019-11-10","cited_by_count":64},{"id":"1808.10122","title":"Learning Neural Templates for Text Generation","created":"2018-08-30","cited_by_count":61},{"id":"1905.13453","title":"MultiQA: An Empirical Investigation of Generalization and Transfer in Reading Comprehension","created":"2019-05-31","cited_by_count":60},{"id":"2106.10502","title":"JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs","created":"2021-06-19","cited_by_count":58},{"id":"1711.09724","title":"Table-to-text Generation by Structure-aware Seq2seq Learning","created":"2017-11-27","cited_by_count":54},{"id":"1912.03915","title":"Learning Disentangled Representations via Mutual Information Estimation","created":"2019-12-09","cited_by_count":52},{"id":"2006.00693","title":"Improving Disentangled Text Representation Learning with Information-Theoretic Guidance","created":"2020-06-01","cited_by_count":52},{"id":"1908.09022","title":"Neural data-to-text generation: A comparison between pipeline and end-to-end architectures","created":"2019-08-23","cited_by_count":51},{"id":"2004.14579","title":"Logic2Text: High-Fidelity Natural Language Generation from Logical Forms","created":"2020-04-30","cited_by_count":45},{"id":"2009.06207","title":"Contrastive Triple Extraction with Generative Transformer","created":"2020-09-14","cited_by_count":44},{"id":"2006.04702","title":"CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training","created":"2020-06-08","cited_by_count":38},{"id":"2105.02685","title":"A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations","created":"2021-05-06","cited_by_count":37},{"id":"1606.04596","title":"Semi-Supervised Learning for Neural Machine Translation","created":"2016-06-15","cited_by_count":36},{"id":"2108.00577","title":"Logic-Consistency Text Generation from Semantic Parses","created":"2021-08-02","cited_by_count":23},{"id":"2012.14919","title":"WikiTableT: A Large-Scale Data-to-Text Dataset for Generating Wikipedia Article Sections","created":"2020-12-29","cited_by_count":22},{"id":"2102.03556","title":"Neural Data-to-Text Generation with LM-based Text Augmentation","created":"2021-02-06","cited_by_count":22},{"id":"2002.01127","title":"Variational Template Machine for Data-to-Text Generation","created":"2020-02-04","cited_by_count":19},{"id":"2202.13756","title":"Data-to-text Generation with Variational Sequential Planning","created":"2022-02-28","cited_by_count":17},{"id":"1810.02889","title":"Scalable Micro-planned Generation of Discourse from Structured Data","created":"2018-10-05","cited_by_count":12},{"id":"1905.10726","title":"SemBleu: A Robust Metric for AMR Parsing Evaluation","created":"2019-05-26","cited_by_count":12},{"id":"2003.06227","title":"Unsupervised Style and Content Separation by Minimizing Mutual Information for Speech Synthesis","created":"2020-03-09","cited_by_count":11},{"id":"2110.02891","title":"Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models","created":"2021-10-06","cited_by_count":11},{"id":"1806.04402","title":"Explaining and Generalizing Back-Translation through Wake-Sleep","created":"2018-06-12","cited_by_count":7},{"id":"2012.07412","title":"Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings","created":"2020-12-14","cited_by_count":5},{"id":"2110.03318","title":"On the Latent Holes of VAEs for Text Generation","created":"2021-10-07","cited_by_count":4},{"id":"2202.06041","title":"A multi-task semi-supervised framework for Text2Graph & Graph2Text","created":"2022-02-12","cited_by_count":1}],"next_cursor":null}