{"list":"other","total":75,"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"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":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"1811.01241","title":"Wizard of Wikipedia: Knowledge-Powered Conversational agents","created":"2018-11-03","cited_by_count":530},{"id":"1611.04558","title":"Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation","created":"2016-11-14","cited_by_count":469},{"id":"1905.07553","title":"Which Tasks Should Be Learned Together in Multi-task Learning?","created":"2019-05-18","cited_by_count":375},{"id":"2009.09796","title":"Multi-Task Learning with Deep Neural Networks: A Survey","created":"2020-09-10","cited_by_count":375},{"id":"1911.06136","title":"KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation","created":"2019-11-13","cited_by_count":356},{"id":"1901.11504","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","created":"2019-01-31","cited_by_count":350},{"id":"1907.05019","title":"Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges","created":"2019-07-11","cited_by_count":257},{"id":"2109.04617","title":"Efficiently Identifying Task Groupings for Multi-Task Learning","created":"2021-09-10","cited_by_count":222},{"id":"2101.11038","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","created":"2021-01-26","cited_by_count":192},{"id":"1710.06481","title":"Constructing Datasets for Multi-hop Reading Comprehension Across Documents","created":"2017-10-17","cited_by_count":190},{"id":"2103.06332","title":"Hurdles to Progress in Long-form Question Answering","created":"2021-03-10","cited_by_count":167},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161},{"id":"1911.12423","title":"AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning","created":"2019-11-27","cited_by_count":160},{"id":"1605.05101","title":"Recurrent Neural Network for Text Classification with Multi-Task Learning","created":"2016-05-17","cited_by_count":144},{"id":"1905.12688","title":"Choosing Transfer Languages for Cross-Lingual Learning","created":"2019-05-29","cited_by_count":144},{"id":"1609.01454","title":"Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling","created":"2016-09-06","cited_by_count":137},{"id":"2010.04389","title":"A Survey of Knowledge-Enhanced Text Generation","created":"2020-10-09","cited_by_count":120},{"id":"1909.02188","title":"A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding","created":"2019-09-05","cited_by_count":107},{"id":"2004.07202","title":"Entities as Experts: Sparse Memory Access with Entity Supervision","created":"2020-04-15","cited_by_count":100},{"id":"1511.06114","title":"Multi-task Sequence to Sequence Learning","created":"2015-11-19","cited_by_count":94},{"id":"1704.05742","title":"Adversarial Multi-task Learning for Text Classification","created":"2017-04-19","cited_by_count":91},{"id":"1906.05572","title":"Proactive Human-Machine Conversation with Explicit Conversation Goals","created":"2019-06-13","cited_by_count":88},{"id":"2002.07510","title":"Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue","created":"2020-02-18","cited_by_count":82},{"id":"1809.08370","title":"Semi-Supervised Sequence Modeling with Cross-View Training","created":"2018-09-22","cited_by_count":75},{"id":"1812.09471","title":"Joint Slot Filling and Intent Detection via Capsule Neural Networks","created":"2018-12-22","cited_by_count":73},{"id":"2009.13818","title":"A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation","created":"2020-09-29","cited_by_count":72},{"id":"2110.04330","title":"KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering","created":"2021-10-08","cited_by_count":67},{"id":"1909.00156","title":"NCLS: Neural Cross-Lingual Summarization","created":"2019-08-31","cited_by_count":64},{"id":"1611.01587","title":"A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks","created":"2016-11-05","cited_by_count":62},{"id":"2010.03880","title":"A Co-Interactive Transformer for Joint Slot Filling and Intent Detection","created":"2020-10-08","cited_by_count":61},{"id":"1811.06031","title":"A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks","created":"2018-11-14","cited_by_count":54},{"id":"1905.07374","title":"Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs","created":"2019-05-17","cited_by_count":53},{"id":"2103.03095","title":"A Survey on Spoken Language Understanding: Recent Advances and New Frontiers","created":"2021-03-04","cited_by_count":53},{"id":"2106.09017","title":"Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation","created":"2021-06-16","cited_by_count":50},{"id":"2105.07316","title":"From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding","created":"2021-05-15","cited_by_count":43},{"id":"2110.06490","title":"Dict-BERT: Enhancing Language Model Pre-training with Dictionary","created":"2021-10-13","cited_by_count":38},{"id":"1706.02027","title":"Question Answering and Question Generation as Dual Tasks","created":"2017-06-07","cited_by_count":37},{"id":"1909.06937","title":"CM-Net: A Novel Collaborative Memory Network for Spoken Language Understanding","created":"2019-09-16","cited_by_count":34},{"id":"1910.05069","title":"Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base","created":"2019-10-11","cited_by_count":33},{"id":"2106.01925","title":"GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling","created":"2021-06-03","cited_by_count":33},{"id":"1705.08142","title":"Latent Multi-task Architecture Learning","created":"2017-05-23","cited_by_count":29},{"id":"1808.06876","title":"Adversarial training for multi-context joint entity and relation extraction","created":"2018-08-21","cited_by_count":29},{"id":"1909.01953","title":"Mixture Content Selection for Diverse Sequence Generation","created":"2019-09-04","cited_by_count":27},{"id":"1805.11004","title":"Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation","created":"2018-05-28","cited_by_count":25},{"id":"1711.05116","title":"Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering","created":"2017-11-14","cited_by_count":24},{"id":"1907.02884","title":"Multi-lingual Intent Detection and Slot Filling in a Joint BERT-based Model","created":"2019-07-05","cited_by_count":24},{"id":"1904.04153","title":"AutoSeM: Automatic Task Selection and Mixing in Multi-Task Learning","created":"2019-04-08","cited_by_count":22},{"id":"1704.07156","title":"Semi-supervised Multitask Learning for Sequence Labeling","created":"2017-04-24","cited_by_count":20},{"id":"2203.07285","title":"Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts","created":"2022-03-14","cited_by_count":19},{"id":"1711.08726","title":"Modelling Domain Relationships for Transfer Learning on Retrieval-based Question Answering Systems in E-commerce","created":"2017-11-23","cited_by_count":18},{"id":"2009.13199","title":"Knowledge-Aware Procedural Text Understanding with Multi-Stage Training","created":"2020-09-28","cited_by_count":17},{"id":"1811.01127","title":"Exploiting Explicit Paths for Multi-hop Reading Comprehension","created":"2018-11-02","cited_by_count":16},{"id":"1906.04618","title":"Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension","created":"2019-06-11","cited_by_count":15},{"id":"1909.09265","title":"Cross-lingual Dependency Parsing with Unlabeled Auxiliary Languages","created":"2019-09-20","cited_by_count":13},{"id":"1711.00106","title":"DCN+: Mixed Objective and Deep Residual Coattention for Question Answering","created":"2017-10-31","cited_by_count":12},{"id":"1808.10628","title":"Retrieve-and-Read: Multi-task Learning of Information Retrieval and Reading Comprehension","created":"2018-08-31","cited_by_count":9},{"id":"1910.03484","title":"Semi-Supervised Neural Text Generation by Joint Learning of Natural Language Generation and Natural Language Understanding Models","created":"2019-09-29","cited_by_count":9},{"id":"1809.06963","title":"Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension","created":"2018-09-18","cited_by_count":8},{"id":"1911.02739","title":"DCA: Diversified Co-Attention towards Informative Live Video Commenting","created":"2019-11-07","cited_by_count":8},{"id":"2009.13401","title":"Injecting Entity Types into Entity-Guided Text Generation","created":"2020-09-28","cited_by_count":7},{"id":"2109.05748","title":"GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks","created":"2021-09-13","cited_by_count":7},{"id":"2005.02557","title":"Crossing Variational Autoencoders for Answer Retrieval","created":"2020-05-06","cited_by_count":5},{"id":"1805.06145","title":"Joint Training of Candidate Extraction and Answer Selection for Reading Comprehension","created":"2018-05-16","cited_by_count":4},{"id":"1810.12264","title":"Learning Comment Generation by Leveraging User-Generated Data","created":"2018-10-29","cited_by_count":3},{"id":"2006.09336","title":"Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks","created":"2020-06-16","cited_by_count":2}],"next_cursor":null}