{"list":"other","total":88,"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":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"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":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"2003.11080","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","created":"2020-03-24","cited_by_count":742},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"1604.03539","title":"Cross-stitch Networks for Multi-task Learning","created":"2016-04-12","cited_by_count":467},{"id":"2005.00052","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","created":"2020-04-30","cited_by_count":445},{"id":"1808.09602","title":"Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction","created":"2018-08-29","cited_by_count":322},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284},{"id":"2004.01401","title":"XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation","created":"2020-04-03","cited_by_count":222},{"id":"2010.05874","title":"Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models","created":"2020-10-12","cited_by_count":169},{"id":"1909.00964","title":"Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks","created":"2019-09-03","cited_by_count":96},{"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":"1907.04829","title":"BAM! Born-Again Multi-Task Networks for Natural Language Understanding","created":"2019-07-10","cited_by_count":85},{"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":"1806.03713","title":"All-in-one: Multi-task Learning for Rumour Verification","created":"2018-06-10","cited_by_count":54},{"id":"1811.06031","title":"A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks","created":"2018-11-14","cited_by_count":54},{"id":"1804.00079","title":"Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning","created":"2018-03-30","cited_by_count":52},{"id":"1906.06906","title":"An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis","created":"2019-06-17","cited_by_count":52},{"id":"2009.09139","title":"Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data","created":"2020-09-19","cited_by_count":50},{"id":"1911.10438","title":"CopyMTL: Copy Mechanism for Joint Extraction of Entities and Relations with Multi-Task Learning","created":"2019-11-24","cited_by_count":47},{"id":"2010.02523","title":"Multi-task Learning for Multilingual Neural Machine Translation","created":"2020-10-06","cited_by_count":46},{"id":"1611.06204","title":"Visualizing and Understanding Curriculum Learning for Long Short-Term Memory Networks","created":"2016-11-18","cited_by_count":44},{"id":"1512.08422","title":"Natural Language Inference by Tree-Based Convolution and Heuristic Matching","created":"2015-12-28","cited_by_count":43},{"id":"1905.08511","title":"Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction","created":"2019-05-21","cited_by_count":39},{"id":"1412.7489","title":"A Unified Perspective on Multi-Domain and Multi-Task Learning","created":"2014-12-23","cited_by_count":33},{"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":"1806.04357","title":"Multi-Task Neural Models for Translating Between Styles Within and Across Languages","created":"2018-06-12","cited_by_count":28},{"id":"1805.11004","title":"Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation","created":"2018-05-28","cited_by_count":25},{"id":"1806.07304","title":"Dynamic Multi-Level Multi-Task Learning for Sentence Simplification","created":"2018-06-19","cited_by_count":25},{"id":"1906.05226","title":"Continual and Multi-Task Architecture Search","created":"2019-06-12","cited_by_count":22},{"id":"1612.02251","title":"When is multitask learning effective? Semantic sequence prediction under varying data conditions","created":"2016-12-07","cited_by_count":21},{"id":"1704.07156","title":"Semi-supervised Multitask Learning for Sequence Labeling","created":"2017-04-24","cited_by_count":20},{"id":"1812.06081","title":"A Neural Multi-Task Learning Framework to Jointly Model Medical Named Entity Recognition and Normalization","created":"2018-12-14","cited_by_count":20},{"id":"1908.05378","title":"Multi-Task Self-Supervised Learning for Disfluency Detection","created":"2019-08-15","cited_by_count":20},{"id":"1910.00458","title":"MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension","created":"2019-10-01","cited_by_count":20},{"id":"1802.08969","title":"Meta Multi-Task Learning for Sequence Modeling","created":"2018-02-25","cited_by_count":18},{"id":"1912.09084","title":"Neural Simile Recognition with Cyclic Multitask Learning and Local Attention","created":"2019-12-19","cited_by_count":18},{"id":"1704.07489","title":"Multi-Task Video Captioning with Video and Entailment Generation","created":"2017-04-24","cited_by_count":17},{"id":"1807.05013","title":"Multi-task dialog act and sentiment recognition on Mastodon","created":"2018-07-13","cited_by_count":15},{"id":"1808.04151","title":"Multi-Task Learning for Sequence Tagging: An Empirical Study","created":"2018-08-13","cited_by_count":15},{"id":"2009.11982","title":"Type B Reflexivization as an Unambiguous Testbed for Multilingual Multi-Task Gender Bias","created":"2020-09-24","cited_by_count":15},{"id":"1506.07190","title":"Multi-domain Dialog State Tracking using Recurrent Neural Networks","created":"2015-06-23","cited_by_count":14},{"id":"1902.01385","title":"Embodied Multimodal Multitask Learning","created":"2019-02-04","cited_by_count":13},{"id":"1603.02776","title":"Implicit Discourse Relation Classification via Multi-Task Neural Networks","created":"2016-03-09","cited_by_count":12},{"id":"2005.10678","title":"Worse WER, but Better BLEU? Leveraging Word Embedding as Intermediate in Multitask End-to-End Speech Translation","created":"2020-05-21","cited_by_count":12},{"id":"2006.04016","title":"A Multitask Learning Approach for Diacritic Restoration","created":"2020-06-07","cited_by_count":12},{"id":"1812.02354","title":"Multi-Task Learning with Multi-View Attention for Answer Selection and Knowledge Base Question Answering","created":"2018-12-06","cited_by_count":11},{"id":"1906.08931","title":"Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data","created":"2019-06-21","cited_by_count":11},{"id":"1907.01791","title":"Multi-Task Networks With Universe, Group, and Task Feature Learning","created":"2019-07-03","cited_by_count":11},{"id":"1909.01720","title":"Different Absorption from the Same Sharing: Sifted Multi-task Learning for Fake News Detection","created":"2019-09-04","cited_by_count":11},{"id":"1704.06855","title":"Deep Multitask Learning for Semantic Dependency Parsing","created":"2017-04-22","cited_by_count":10},{"id":"1805.00287","title":"Multitask Parsing Across Semantic Representations","created":"2018-05-01","cited_by_count":10},{"id":"1908.11052","title":"Zero-shot Text-to-SQL Learning with Auxiliary Task","created":"2019-08-29","cited_by_count":10},{"id":"1908.11813","title":"Multi-Task Learning with Language Modeling for Question Generation","created":"2019-08-30","cited_by_count":10},{"id":"1710.07210","title":"Multi-Task Label Embedding for Text Classification","created":"2017-10-17","cited_by_count":9},{"id":"1804.08139","title":"Same Representation, Different Attentions: Shareable Sentence Representation Learning from Multiple Tasks","created":"2018-04-22","cited_by_count":9},{"id":"1906.01239","title":"Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies","created":"2019-06-04","cited_by_count":9},{"id":"1910.12702","title":"Adversarial Multitask Learning for Joint Multi-Feature and Multi-Dialect Morphological Modeling","created":"2019-10-28","cited_by_count":9},{"id":"1610.07844","title":"Improving historical spelling normalization with bi-directional LSTMs and multi-task learning","created":"2016-10-25","cited_by_count":8},{"id":"1704.00514","title":"Multi-Task Learning of Keyphrase Boundary Classification","created":"2017-04-03","cited_by_count":8},{"id":"2006.02174","title":"CompGuessWhat?!: A Multi-task Evaluation Framework for Grounded Language Learning","created":"2020-06-03","cited_by_count":8},{"id":"1803.11326","title":"Deep Cascade Multi-task Learning for Slot Filling in Online Shopping Assistant","created":"2018-03-30","cited_by_count":7},{"id":"1907.02427","title":"Multi-Task Learning for Coherence Modeling","created":"2019-07-04","cited_by_count":6},{"id":"2005.02473","title":"Efficient strategies for hierarchical text classification: External knowledge and auxiliary tasks","created":"2020-05-05","cited_by_count":6},{"id":"1609.07222","title":"Deep Multi-Task Learning with Shared Memory","created":"2016-09-23","cited_by_count":5},{"id":"1906.00790","title":"Multi-task Pairwise Neural Ranking for Hashtag Segmentation","created":"2019-06-03","cited_by_count":5},{"id":"1911.04641","title":"A Syntax-aware Multi-task Learning Framework for Chinese Semantic Role Labeling","created":"2019-11-12","cited_by_count":5},{"id":"1707.02892","title":"A Generalized Recurrent Neural Architecture for Text Classification with Multi-Task Learning","created":"2017-07-10","cited_by_count":4},{"id":"1906.06849","title":"A Multi-Task Architecture on Relevance-based Neural Query Translation","created":"2019-06-17","cited_by_count":4},{"id":"1809.06748","title":"Transfer and Multi-Task Learning for Noun-Noun Compound Interpretation","created":"2018-09-18","cited_by_count":3},{"id":"1811.11456","title":"GIRNet: Interleaved Multi-Task Recurrent State Sequence Models","created":"2018-11-28","cited_by_count":3},{"id":"2003.04994","title":"Masking Orchestration: Multi-task Pretraining for Multi-role Dialogue Representation Learning","created":"2020-02-27","cited_by_count":3},{"id":"1809.08928","title":"Joint Multitask Learning for Community Question Answering Using Task-Specific Embeddings","created":"2018-09-24","cited_by_count":2},{"id":"1805.02914","title":"One \"Ruler\" for All Languages: Multi-Lingual Dialogue Evaluation with Adversarial Multi-Task Learning","created":"2018-05-08","cited_by_count":1},{"id":"2004.14961","title":"Mutlitask Learning for Cross-Lingual Transfer of Semantic Dependencies","created":"2020-04-30","cited_by_count":1}],"next_cursor":null}