{"list":"other","total":125,"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":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"1711.09601","title":"Memory Aware Synapses: Learning what (not) to forget","created":"2017-11-27","cited_by_count":1105},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1710.03463","title":"Learning to Generalize: Meta-Learning for Domain Generalization","created":"2017-10-10","cited_by_count":763},{"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":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"2104.08164","title":"Editing Factual Knowledge in Language Models","created":"2021-04-16","cited_by_count":553},{"id":"1805.06370","title":"Progress & Compress: A scalable framework for continual learning","created":"2018-05-16","cited_by_count":520},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"2103.09762","title":"Gradient Projection Memory for Continual Learning","created":"2021-03-17","cited_by_count":348},{"id":"1903.03096","title":"Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples","created":"2019-03-07","cited_by_count":315},{"id":"1810.09502","title":"How to train your MAML","created":"2018-10-22","cited_by_count":309},{"id":"1810.03548","title":"Meta-Learning: A Survey","created":"2018-10-08","cited_by_count":256},{"id":"1906.01076","title":"Episodic Memory in Lifelong Language Learning","created":"2019-06-03","cited_by_count":188},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180},{"id":"2110.07814","title":"Meta-learning via Language Model In-context Tuning","created":"2021-10-15","cited_by_count":164},{"id":"1909.03329","title":"LAMOL: LAnguage MOdeling for Lifelong Language Learning","created":"2019-09-07","cited_by_count":160},{"id":"1901.05335","title":"A review of domain adaptation without target labels","created":"2019-01-16","cited_by_count":156},{"id":"2004.00345","title":"Editable Neural Networks","created":"2020-04-01","cited_by_count":155},{"id":"2104.08835","title":"CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP","created":"2021-04-18","cited_by_count":142},{"id":"2005.14187","title":"HAT: Hardware-Aware Transformers for Efficient Natural Language Processing","created":"2020-05-28","cited_by_count":136},{"id":"1911.03809","title":"Meta Label Correction for Noisy Label Learning","created":"2019-11-10","cited_by_count":108},{"id":"1808.08437","title":"Meta-Learning for Low-Resource Neural Machine Translation","created":"2018-08-25","cited_by_count":105},{"id":"2010.03522","title":"A Survey of Deep Meta-Learning","created":"2020-10-07","cited_by_count":100},{"id":"1910.07124","title":"FewRel 2.0: Towards More Challenging Few-Shot Relation Classification","created":"2019-10-16","cited_by_count":94},{"id":"1905.10033","title":"Personalizing Dialogue Agents via Meta-Learning","created":"2019-05-24","cited_by_count":83},{"id":"2006.05702","title":"Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network","created":"2020-06-10","cited_by_count":83},{"id":"1808.09040","title":"One-Shot Relational Learning for Knowledge Graphs","created":"2018-08-27","cited_by_count":78},{"id":"1909.01515","title":"Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs","created":"2019-09-04","cited_by_count":73},{"id":"2004.06748","title":"Balancing Training for Multilingual Neural Machine Translation","created":"2020-04-14","cited_by_count":72},{"id":"2010.03546","title":"Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing","created":"2020-10-07","cited_by_count":72},{"id":"2107.07170","title":"FLEX: Unifying Evaluation for Few-Shot NLP","created":"2021-07-15","cited_by_count":67},{"id":"2003.02739","title":"Zero-Shot Cross-Lingual Transfer with Meta Learning","created":"2020-03-05","cited_by_count":66},{"id":"1902.10482","title":"Induction Networks for Few-Shot Text Classification","created":"2019-02-27","cited_by_count":64},{"id":"1911.11298","title":"Few-Shot Knowledge Graph Completion","created":"2019-11-26","cited_by_count":63},{"id":"2106.04252","title":"Meta-Learning to Compositionally Generalize","created":"2021-06-08","cited_by_count":62},{"id":"1805.07513","title":"Diverse Few-Shot Text Classification with Multiple Metrics","created":"2018-05-19","cited_by_count":61},{"id":"2106.04570","title":"BERT Learns to Teach: Knowledge Distillation with Meta Learning","created":"2021-06-08","cited_by_count":61},{"id":"1911.03863","title":"Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks","created":"2019-11-10","cited_by_count":57},{"id":"2007.05549","title":"Meta-Learning Requires Meta-Augmentation","created":"2020-07-10","cited_by_count":57},{"id":"2105.14444","title":"NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search","created":"2021-05-30","cited_by_count":56},{"id":"2007.13040","title":"Improving Generalization in Meta-learning via Task Augmentation","created":"2020-07-26","cited_by_count":55},{"id":"2001.04246","title":"AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search","created":"2020-01-13","cited_by_count":51},{"id":"2009.08445","title":"Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Tasks","created":"2020-09-17","cited_by_count":51},{"id":"1908.10423","title":"Investigating Meta-Learning Algorithms for Low-Resource Natural Language Understanding Tasks","created":"2019-08-27","cited_by_count":48},{"id":"2010.02500","title":"Efficient Meta Lifelong-Learning with Limited Memory","created":"2020-10-06","cited_by_count":48},{"id":"1809.10460","title":"Sample Efficient Adaptive Text-to-Speech","created":"2018-09-27","cited_by_count":45},{"id":"2106.02695","title":"Meta-Learning with Fewer Tasks through Task Interpolation","created":"2021-06-04","cited_by_count":45},{"id":"2007.09604","title":"Meta-learning for Few-shot Natural Language Processing: A Survey","created":"2020-07-19","cited_by_count":42},{"id":"2010.09638","title":"Adaptive Attentional Network for Few-Shot Knowledge Graph Completion","created":"2020-10-19","cited_by_count":42},{"id":"1906.03520","title":"Domain Adaptive Dialog Generation via Meta Learning","created":"2019-06-08","cited_by_count":41},{"id":"2010.11988","title":"Meta-Learning for Domain Generalization in Semantic Parsing","created":"2020-10-22","cited_by_count":41},{"id":"2010.07092","title":"Data Augmentation for Meta-Learning","created":"2020-10-14","cited_by_count":38},{"id":"1909.05357","title":"Out-of-Domain Detection for Low-Resource Text Classification Tasks","created":"2019-08-31","cited_by_count":36},{"id":"1802.10542","title":"Memory-based Parameter Adaptation","created":"2018-02-28","cited_by_count":35},{"id":"1909.04176","title":"Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification","created":"2019-09-09","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":"1803.02400","title":"Natural Language to Structured Query Generation via Meta-Learning","created":"2018-03-02","cited_by_count":33},{"id":"2012.01266","title":"Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains","created":"2020-12-02","cited_by_count":33},{"id":"1906.06678","title":"Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification","created":"2019-06-16","cited_by_count":32},{"id":"1907.00505","title":"Few-Shot Representation Learning for Out-Of-Vocabulary Words","created":"2019-07-01","cited_by_count":30},{"id":"1908.11513","title":"Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations","created":"2019-08-30","cited_by_count":30},{"id":"1906.00794","title":"Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion","created":"2019-06-03","cited_by_count":29},{"id":"1910.12094","title":"Meta Learning for End-to-End Low-Resource Speech Recognition","created":"2019-10-26","cited_by_count":29},{"id":"2003.01901","title":"Learning Fast Adaptation on Cross-Accented Speech Recognition","created":"2020-03-04","cited_by_count":28},{"id":"1905.05644","title":"Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems","created":"2019-05-14","cited_by_count":25},{"id":"1911.06161","title":"Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resources","created":"2019-11-14","cited_by_count":25},{"id":"1912.09867","title":"Meta-Graph: Few Shot Link Prediction via Meta Learning","created":"2019-12-20","cited_by_count":24},{"id":"2005.05727","title":"Dynamic Memory Induction Networks for Few-Shot Text Classification","created":"2020-05-12","cited_by_count":23},{"id":"1906.05226","title":"Continual and Multi-Task Architecture Search","created":"2019-06-12","cited_by_count":22},{"id":"2004.14228","title":"Meta-Transfer Learning for Code-Switched Speech Recognition","created":"2020-04-29","cited_by_count":22},{"id":"2111.04040","title":"Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech","created":"2021-11-07","cited_by_count":22},{"id":"2104.07908","title":"MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning","created":"2021-04-16","cited_by_count":21},{"id":"1909.11359","title":"Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion","created":"2019-09-25","cited_by_count":19},{"id":"1906.07108","title":"Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing","created":"2019-06-17","cited_by_count":18},{"id":"2007.14463","title":"Few-Shot Keyword Spotting With Prototypical Networks","created":"2020-07-25","cited_by_count":18},{"id":"1912.05467","title":"MetaMT,a MetaLearning Method Leveraging Multiple Domain Data for Low Resource Machine Translation","created":"2019-12-11","cited_by_count":17},{"id":"2010.15877","title":"Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning","created":"2020-10-29","cited_by_count":16},{"id":"2101.06779","title":"Few Shot Dialogue State Tracking using Meta-learning","created":"2021-01-17","cited_by_count":16},{"id":"2102.07847","title":"Meta Back-translation","created":"2021-02-15","cited_by_count":16},{"id":"2105.03070","title":"SpeechNet: A Universal Modularized Model for Speech Processing Tasks","created":"2021-05-07","cited_by_count":16},{"id":"2107.05176","title":"Zero-Shot Compositional Concept Learning","created":"2021-07-12","cited_by_count":16},{"id":"2005.07029","title":"DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation","created":"2020-05-13","cited_by_count":15},{"id":"2012.11896","title":"Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition","created":"2020-12-22","cited_by_count":15}],"next_cursor":"100"}