{"list":"other","total":59,"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":"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":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"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":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"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":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2004.09813","title":"Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation","created":"2020-04-21","cited_by_count":593},{"id":"1905.12616","title":"Defending Against Neural Fake News","created":"2019-05-29","cited_by_count":559},{"id":"1908.04319","title":"Neural Text Generation with Unlikelihood Training","created":"2019-08-12","cited_by_count":503},{"id":"1711.02281","title":"Non-Autoregressive Neural Machine Translation","created":"2017-11-07","cited_by_count":463},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441},{"id":"2009.06367","title":"GeDi: Generative Discriminator Guided Sequence Generation","created":"2020-09-14","cited_by_count":378},{"id":"1609.05473","title":"SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient","created":"2016-09-18","cited_by_count":376},{"id":"2104.05218","title":"FUDGE: Controlled Text Generation With Future Discriminators","created":"2021-04-12","cited_by_count":376},{"id":"2104.13346","title":"Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics","created":"2021-04-27","cited_by_count":287},{"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":"1704.07138","title":"Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search","created":"2017-04-24","cited_by_count":237},{"id":"1912.12854","title":"Pareto Multi-Task Learning","created":"2019-12-30","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":"1804.00344","title":"Marian: Fast Neural Machine Translation in C++","created":"2018-04-01","cited_by_count":203},{"id":"1804.06437","title":"Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer","created":"2018-04-17","cited_by_count":191},{"id":"2010.05700","title":"Reformulating Unsupervised Style Transfer as Paraphrase Generation","created":"2020-10-12","cited_by_count":183},{"id":"1707.02633","title":"Controlling Linguistic Style Aspects in Neural Language Generation","created":"2017-07-09","cited_by_count":149},{"id":"2010.12884","title":"NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints","created":"2020-10-24","cited_by_count":149},{"id":"1804.09000","title":"Style Transfer Through Back-Translation","created":"2018-04-24","cited_by_count":124},{"id":"1908.10090","title":"On NMT Search Errors and Model Errors: Cat Got Your Tongue?","created":"2019-08-27","cited_by_count":114},{"id":"1909.06694","title":"Beyond BLEU: Training Neural Machine Translation with Semantic Similarity","created":"2019-09-14","cited_by_count":84},{"id":"1908.09368","title":"Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfer","created":"2019-08-25","cited_by_count":81},{"id":"2004.15015","title":"Imitation Attacks and Defenses for Black-box Machine Translation Systems","created":"2020-04-30","cited_by_count":81},{"id":"2010.05906","title":"Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning","created":"2020-10-12","cited_by_count":65},{"id":"2010.13816","title":"PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction","created":"2020-10-26","cited_by_count":59},{"id":"1711.04956","title":"Classical Structured Prediction Losses for Sequence to Sequence Learning","created":"2017-11-14","cited_by_count":55},{"id":"2010.06313","title":"Controllable Pareto Multi-Task Learning","created":"2020-10-13","cited_by_count":51},{"id":"1811.01135","title":"Content preserving text generation with attribute controls","created":"2018-11-03","cited_by_count":47},{"id":"2006.03535","title":"CoCon: A Self-Supervised Approach for Controlled Text Generation","created":"2020-06-05","cited_by_count":47},{"id":"2004.05665","title":"Minimizing FLOPs to Learn Efficient Sparse Representations","created":"2020-04-12","cited_by_count":46},{"id":"2011.04743","title":"Adversarial Semantic Collisions","created":"2020-11-09","cited_by_count":42},{"id":"2004.08361","title":"Unsupervised Discovery of Implicit Gender Bias","created":"2020-04-17","cited_by_count":34},{"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":"1811.00552","title":"Multiple-Attribute Text Style Transfer","created":"2018-11-01","cited_by_count":20},{"id":"2005.00136","title":"Contextual Text Style Transfer","created":"2020-04-30","cited_by_count":17},{"id":"1701.02854","title":"Towards Decoding as Continuous Optimization in Neural Machine Translation","created":"2017-01-11","cited_by_count":15}],"next_cursor":null}