{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"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":"1511.06709","title":"Improving Neural Machine Translation Models with Monolingual Data","created":"2015-11-20","cited_by_count":788},{"id":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"id":"1803.11175","title":"Universal Sentence Encoder","created":"2018-03-29","cited_by_count":489},{"id":"1710.04087","title":"Word Translation Without Parallel Data","created":"2017-10-11","cited_by_count":487},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"2009.06367","title":"GeDi: Generative Discriminator Guided Sequence Generation","created":"2020-09-14","cited_by_count":378},{"id":"1905.02450","title":"MASS: Masked Sequence to Sequence Pre-training for Language Generation","created":"2019-05-07","cited_by_count":347},{"id":"1711.00043","title":"Unsupervised Machine Translation Using Monolingual Corpora Only","created":"2017-10-31","cited_by_count":273},{"id":"1703.00955","title":"Toward Controlled Generation of Text","created":"2017-03-02","cited_by_count":272},{"id":"1705.09655","title":"Style Transfer from Non-Parallel Text by Cross-Alignment","created":"2017-05-26","cited_by_count":248},{"id":"1612.08220","title":"Understanding Neural Networks through Representation Erasure","created":"2016-12-24","cited_by_count":224},{"id":"1803.06535","title":"Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer","created":"2018-03-17","cited_by_count":211},{"id":"1610.08914","title":"Ex Machina: Personal Attacks Seen at Scale","created":"2016-10-27","cited_by_count":210},{"id":"1903.08983","title":"SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)","created":"2019-03-19","cited_by_count":207},{"id":"1804.06437","title":"Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer","created":"2018-04-17","cited_by_count":191},{"id":"1912.05372","title":"FlauBERT: Unsupervised Language Model Pre-training for French","created":"2019-12-11","cited_by_count":153},{"id":"1707.02633","title":"Controlling Linguistic Style Aspects in Neural Language Generation","created":"2017-07-09","cited_by_count":149},{"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":"1711.06861","title":"Style Transfer in Text: Exploration and Evaluation","created":"2017-11-18","cited_by_count":146},{"id":"1804.07755","title":"Phrase-Based & Neural Unsupervised Machine Translation","created":"2018-04-20","cited_by_count":138},{"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":"1911.09709","title":"Automatically Neutralizing Subjective Bias in Text","created":"2019-11-21","cited_by_count":105},{"id":"1909.02480","title":"FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow","created":"2019-09-05","cited_by_count":89},{"id":"1905.05621","title":"Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation","created":"2019-05-14","cited_by_count":84},{"id":"1805.05345","title":"Conversations Gone Awry: Detecting Early Signs of Conversational Failure","created":"2018-05-14","cited_by_count":73},{"id":"1805.11749","title":"Unsupervised Text Style Transfer using Language Models as Discriminators","created":"2018-05-30","cited_by_count":70},{"id":"2002.03912","title":"A Probabilistic Formulation of Unsupervised Text Style Transfer","created":"2020-02-10","cited_by_count":70},{"id":"1905.10060","title":"A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer","created":"2019-05-24","cited_by_count":65},{"id":"1805.05181","title":"Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach","created":"2018-05-14","cited_by_count":55},{"id":"1805.07685","title":"Fighting Offensive Language on Social Media with Unsupervised Text Style Transfer","created":"2018-05-20","cited_by_count":55},{"id":"1611.08002","title":"Semantic Compositional Networks for Visual Captioning","created":"2016-11-23","cited_by_count":50},{"id":"1908.08039","title":"\"Mask and Infill\" : Applying Masked Language Model to Sentiment Transfer","created":"2019-08-21","cited_by_count":48},{"id":"1811.01135","title":"Content preserving text generation with attribute controls","created":"2018-11-03","cited_by_count":47},{"id":"1903.10671","title":"Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus","created":"2019-03-26","cited_by_count":38},{"id":"1709.02349","title":"A Deep Reinforcement Learning Chatbot","created":"2017-09-07","cited_by_count":36},{"id":"1905.12926","title":"Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation","created":"2019-05-30","cited_by_count":34},{"id":"1901.11333","title":"IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation","created":"2019-01-31","cited_by_count":33},{"id":"2004.10454","title":"A Study of Non-autoregressive Model for Sequence Generation","created":"2020-04-22","cited_by_count":31},{"id":"1812.04616","title":"Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs","created":"2018-12-10","cited_by_count":27},{"id":"1904.03651","title":"SEQ^3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression","created":"2019-04-07","cited_by_count":27},{"id":"1801.05617","title":"Automatic Detection of Cyberbullying in Social Media Text","created":"2018-01-17","cited_by_count":26},{"id":"1905.12304","title":"Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning","created":"2019-05-29","cited_by_count":21},{"id":"1906.01833","title":"A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer","created":"2019-06-05","cited_by_count":20},{"id":"1808.07894","title":"Style Transfer as Unsupervised Machine Translation","created":"2018-08-23","cited_by_count":19},{"id":"1805.07143","title":"Style Obfuscation by Invariance","created":"2018-05-18","cited_by_count":10},{"id":"1808.07311","title":"Learning Sentiment Memories for Sentiment Modification without Parallel Data","created":"2018-08-22","cited_by_count":10},{"id":"1910.00998","title":"SummAE: Zero-Shot Abstractive Text Summarization using Length-Agnostic Auto-Encoders","created":"2019-10-02","cited_by_count":7}],"next_cursor":null}