{"list":"other","total":54,"rows":[{"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":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"1906.02691","title":"An Introduction to Variational Autoencoders","created":"2019-06-06","cited_by_count":1000},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"id":"1511.06709","title":"Improving Neural Machine Translation Models with Monolingual Data","created":"2015-11-20","cited_by_count":788},{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409},{"id":"1812.02230","title":"Towards a Definition of Disentangled Representations","created":"2018-12-05","cited_by_count":296},{"id":"2010.15980","title":"AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts","created":"2020-10-29","cited_by_count":249},{"id":"1705.07120","title":"VAE with a VampPrior","created":"2017-05-19","cited_by_count":248},{"id":"1611.02648","title":"Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders","created":"2016-11-08","cited_by_count":220},{"id":"1906.01076","title":"Episodic Memory in Lifelong Language Learning","created":"2019-06-03","cited_by_count":188},{"id":"1911.03118","title":"Not Enough Data? Deep Learning to the Rescue!","created":"2019-11-08","cited_by_count":175},{"id":"2003.02245","title":"Data Augmentation using Pre-trained Transformer Models","created":"2020-03-04","cited_by_count":168},{"id":"2011.00416","title":"Deep Learning for Text Style Transfer: A Survey","created":"2020-11-01","cited_by_count":162},{"id":"2012.09823","title":"Continual Lifelong Learning in Natural Language Processing: A Survey","created":"2020-12-17","cited_by_count":152},{"id":"2004.03829","title":"Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning","created":"2020-04-08","cited_by_count":139},{"id":"2201.05337","title":"A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models","created":"2022-01-14","cited_by_count":129},{"id":"1808.04339","title":"Disentangled Representation Learning for Non-Parallel Text Style Transfer","created":"2018-08-13","cited_by_count":127},{"id":"2004.04092","title":"Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space","created":"2020-04-05","cited_by_count":114},{"id":"1812.06705","title":"Conditional BERT Contextual Augmentation","created":"2018-12-17","cited_by_count":107},{"id":"2104.05489","title":"Continual Learning for Text Classification with Information Disentanglement Based Regularization","created":"2021-04-12","cited_by_count":86},{"id":"2109.03795","title":"Desiderata for Representation Learning: A Causal Perspective","created":"2021-09-08","cited_by_count":76},{"id":"1903.02588","title":"Sentence Embedding Alignment for Lifelong Relation Extraction","created":"2019-03-06","cited_by_count":70},{"id":"1904.02295","title":"Evaluating Style Transfer for Text","created":"2019-04-04","cited_by_count":61},{"id":"2005.01822","title":"Exploring Controllable Text Generation Techniques","created":"2020-05-04","cited_by_count":55},{"id":"2102.01335","title":"Neural Data Augmentation via Example Extrapolation","created":"2021-02-02","cited_by_count":54},{"id":"1906.03785","title":"Generalized Data Augmentation for Low-Resource Translation","created":"2019-06-10","cited_by_count":53},{"id":"2006.00693","title":"Improving Disentangled Text Representation Learning with Information-Theoretic Guidance","created":"2020-06-01","cited_by_count":52},{"id":"1810.10665","title":"Engaging Image Captioning Via Personality","created":"2018-10-25","cited_by_count":51},{"id":"1806.10069","title":"Deep $k$-Means: Jointly clustering with $k$-Means and learning representations","created":"2018-06-26","cited_by_count":50},{"id":"2011.11928","title":"GLGE: A New General Language Generation Evaluation Benchmark","created":"2020-11-24","cited_by_count":47},{"id":"2112.03271","title":"Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks","created":"2021-12-06","cited_by_count":46},{"id":"1910.04176","title":"A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification","created":"2019-10-09","cited_by_count":45},{"id":"2201.09119","title":"A Causal Lens for Controllable Text Generation","created":"2022-01-22","cited_by_count":45},{"id":"2009.13028","title":"Mitigating Gender Bias for Neural Dialogue Generation with Adversarial Learning","created":"2020-09-28","cited_by_count":44},{"id":"2010.01794","title":"GenAug: Data Augmentation for Finetuning Text Generators","created":"2020-10-05","cited_by_count":41},{"id":"1904.09408","title":"Language Models with Transformers","created":"2019-04-20","cited_by_count":36},{"id":"2108.07668","title":"Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation","created":"2021-08-17","cited_by_count":35},{"id":"2101.01926","title":"Curriculum-Meta Learning for Order-Robust Continual Relation Extraction","created":"2021-01-06","cited_by_count":34},{"id":"2103.09420","title":"Improving Zero-shot Voice Style Transfer via Disentangled Representation Learning","created":"2021-03-17","cited_by_count":32},{"id":"2003.08561","title":"XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning","created":"2020-03-19","cited_by_count":31},{"id":"2004.11967","title":"Defining Benchmarks for Continual Few-Shot Learning","created":"2020-04-15","cited_by_count":21},{"id":"2110.07385","title":"Few-shot Controllable Style Transfer for Low-Resource Multilingual Settings","created":"2021-10-14","cited_by_count":21},{"id":"1808.09042","title":"Adversarial Decomposition of Text Representation","created":"2018-08-27","cited_by_count":18},{"id":"2005.00146","title":"Addressing Catastrophic Forgetting in Few-Shot Problems","created":"2020-04-30","cited_by_count":12},{"id":"2109.05186","title":"Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers","created":"2021-09-11","cited_by_count":9},{"id":"1905.00921","title":"Continuous Learning for Large-scale Personalized Domain Classification","created":"2019-05-02","cited_by_count":4},{"id":"1911.03914","title":"Zero-Shot Fine-Grained Style Transfer: Leveraging Distributed Continuous Style Representations to Transfer To Unseen Styles","created":"2019-11-10","cited_by_count":2}],"next_cursor":null}