{"list":"other","total":52,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"1607.01759","title":"Bag of Tricks for Efficient Text Classification","created":"2016-07-06","cited_by_count":876},{"id":"1804.10959","title":"Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates","created":"2018-04-29","cited_by_count":639},{"id":"1505.00853","title":"Empirical Evaluation of Rectified Activations in Convolutional Network","created":"2015-05-05","cited_by_count":519},{"id":"1902.00146","title":"Agnostic Federated Learning","created":"2019-02-01","cited_by_count":456},{"id":"1610.08452","title":"Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment","created":"2016-10-26","cited_by_count":369},{"id":"1612.03651","title":"FastText.zip: Compressing text classification models","created":"2016-12-12","cited_by_count":335},{"id":"1804.03599","title":"Understanding disentangling in $\\beta$-VAE","created":"2018-04-10","cited_by_count":335},{"id":"1703.00955","title":"Toward Controlled Generation of Text","created":"2017-03-02","cited_by_count":272},{"id":"2006.12013","title":"CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information","created":"2020-06-22","cited_by_count":235},{"id":"1608.08868","title":"Demographic Dialectal Variation in Social Media: A Case Study of African-American English","created":"2016-08-31","cited_by_count":196},{"id":"1804.06437","title":"Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer","created":"2018-04-17","cited_by_count":191},{"id":"1808.06640","title":"Adversarial Removal of Demographic Attributes from Text Data","created":"2018-08-20","cited_by_count":170},{"id":"1711.06861","title":"Style Transfer in Text: Exploration and Evaluation","created":"2017-11-18","cited_by_count":146},{"id":"1705.10915","title":"Unsupervised Learning of Disentangled Representations from Video","created":"2017-05-31","cited_by_count":139},{"id":"1705.11122","title":"Controllable Invariance through Adversarial Feature Learning","created":"2017-05-31","cited_by_count":127},{"id":"1808.04339","title":"Disentangled Representation Learning for Non-Parallel Text Style Transfer","created":"2018-08-13","cited_by_count":127},{"id":"1804.09000","title":"Style Transfer Through Back-Translation","created":"2018-04-24","cited_by_count":124},{"id":"1806.04166","title":"Learning to Decompose and Disentangle Representations for Video Prediction","created":"2018-06-11","cited_by_count":121},{"id":"1712.03878","title":"Generalized Zero-Shot Learning via Synthesized Examples","created":"2017-12-11","cited_by_count":114},{"id":"1905.12506","title":"Are Disentangled Representations Helpful for Abstract Visual Reasoning?","created":"2019-05-29","cited_by_count":100},{"id":"1907.05789","title":"Generating Sentences from Disentangled Syntactic and Semantic Spaces","created":"2019-07-06","cited_by_count":59},{"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":"1904.02793","title":"Affect-Driven Dialog Generation","created":"2019-04-04","cited_by_count":50},{"id":"1301.7745","title":"Equitability, mutual information, and the maximal information coefficient","created":"2013-01-31","cited_by_count":45},{"id":"2005.07522","title":"Parallel Data Augmentation for Formality Style Transfer","created":"2020-05-14","cited_by_count":39},{"id":"2009.11152","title":"Hierarchical Pre-training for Sequence Labelling in Spoken Dialog","created":"2020-09-23","cited_by_count":36},{"id":"1706.01847","title":"Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext","created":"2017-06-06","cited_by_count":27},{"id":"2002.08801","title":"Guiding attention in Sequence-to-sequence models for Dialogue Act prediction","created":"2020-02-20","cited_by_count":26},{"id":"1908.06809","title":"Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites","created":"2019-08-19","cited_by_count":20},{"id":"2003.11593","title":"Heavy-tailed Representations, Text Polarity Classification & Data Augmentation","created":"2020-03-25","cited_by_count":20},{"id":"1903.06353","title":"Formality Style Transfer with Hybrid Textual Annotations","created":"2019-03-15","cited_by_count":16},{"id":"2009.11340","title":"The importance of fillers for text representations of speech transcripts","created":"2020-09-23","cited_by_count":15},{"id":"1908.11216","title":"From the Token to the Review: A Hierarchical Multimodal approach to Opinion Mining","created":"2019-08-29","cited_by_count":14},{"id":"1804.04093","title":"SHAPED: Shared-Private Encoder-Decoder for Text Style Adaptation","created":"2018-04-11","cited_by_count":11},{"id":"1809.04556","title":"Unsupervised Controllable Text Formalization","created":"2018-09-10","cited_by_count":9},{"id":"1802.09386","title":"Learning Anonymized Representations with Adversarial Neural Networks","created":"2018-02-26","cited_by_count":7},{"id":"2002.02851","title":"On the Estimation of Information Measures of Continuous Distributions","created":"2020-02-07","cited_by_count":6},{"id":"1811.03271","title":"Learning Disentangled Representations for Timber and Pitch in Music Audio","created":"2018-11-08","cited_by_count":4},{"id":"1909.12928","title":"Decomposing Textual Information For Style Transfer","created":"2019-09-26","cited_by_count":3}],"next_cursor":null}