{"list":"other","total":56,"rows":[{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"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":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"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":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344},{"id":"2010.15980","title":"AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts","created":"2020-10-29","cited_by_count":249},{"id":"2006.05987","title":"Revisiting Few-sample BERT Fine-tuning","created":"2020-06-10","cited_by_count":238},{"id":"2109.04332","title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning","created":"2021-09-09","cited_by_count":232},{"id":"2004.12239","title":"MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification","created":"2020-04-25","cited_by_count":187},{"id":"2104.07650","title":"KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction","created":"2021-04-15","cited_by_count":180},{"id":"2010.08014","title":"GSum: A General Framework for Guided Neural Abstractive Summarization","created":"2020-10-15","cited_by_count":129},{"id":"1905.08941","title":"Augmenting Data with Mixup for Sentence Classification: An Empirical Study","created":"2019-05-22","cited_by_count":125},{"id":"2104.14690","title":"Entailment as Few-Shot Learner","created":"2021-04-29","cited_by_count":123},{"id":"2107.03158","title":"A Survey on Data Augmentation for Text Classification","created":"2021-07-07","cited_by_count":111},{"id":"2106.07499","title":"An Empirical Survey of Data Augmentation for Limited Data Learning in NLP","created":"2021-06-14","cited_by_count":101},{"id":"1806.04734","title":"Delta-encoder: an effective sample synthesis method for few-shot object recognition","created":"2018-06-12","cited_by_count":89},{"id":"2110.01852","title":"Data Augmentation Approaches in Natural Language Processing: A Survey","created":"2021-10-05","cited_by_count":82},{"id":"2104.05832","title":"SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning","created":"2021-04-12","cited_by_count":77},{"id":"1609.05566","title":"Label-Free Supervision of Neural Networks with Physics and Domain Knowledge","created":"2016-09-18","cited_by_count":74},{"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":"1911.03863","title":"Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks","created":"2019-11-10","cited_by_count":57},{"id":"2010.02322","title":"SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup","created":"2020-10-05","cited_by_count":52},{"id":"2202.12499","title":"PromDA: Prompt-based Data Augmentation for Low-Resource NLU Tasks","created":"2022-02-25","cited_by_count":51},{"id":"2004.11546","title":"Generative Data Augmentation for Commonsense Reasoning","created":"2020-04-24","cited_by_count":49},{"id":"2012.02952","title":"Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation","created":"2020-12-05","cited_by_count":47},{"id":"2203.06654","title":"Continual Prompt Tuning for Dialog State Tracking","created":"2022-03-13","cited_by_count":44},{"id":"2007.09604","title":"Meta-learning for Few-shot Natural Language Processing: A Survey","created":"2020-07-19","cited_by_count":42},{"id":"2012.15699","title":"Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuning","created":"2020-12-31","cited_by_count":39},{"id":"2110.06609","title":"MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators","created":"2021-10-13","cited_by_count":35},{"id":"2010.07245","title":"Text Classification Using Label Names Only: A Language Model Self-Training Approach","created":"2020-10-14","cited_by_count":32},{"id":"2108.06332","title":"FlipDA: Effective and Robust Data Augmentation for Few-Shot Learning","created":"2021-08-13","cited_by_count":32},{"id":"2002.03049","title":"Snippext: Semi-supervised Opinion Mining with Augmented Data","created":"2020-02-07","cited_by_count":26},{"id":"2004.01732","title":"Leveraging Multi-Source Weak Social Supervision for Early Detection of Fake News","created":"2020-04-03","cited_by_count":24},{"id":"2205.01543","title":"Learning to Transfer Prompts for Text Generation","created":"2022-05-03","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":"2005.13084","title":"Learning with Weak Supervision for Email Intent Detection","created":"2020-05-26","cited_by_count":17},{"id":"2109.00523","title":"Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification","created":"2021-09-01","cited_by_count":15},{"id":"2205.06153","title":"TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding","created":"2022-05-12","cited_by_count":15},{"id":"2202.13840","title":"Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks","created":"2022-02-28","cited_by_count":13},{"id":"2111.02570","title":"CLUES: Few-Shot Learning Evaluation in Natural Language Understanding","created":"2021-11-04","cited_by_count":9},{"id":"2004.01907","title":"Knowledge Guided Metric Learning for Few-Shot Text Classification","created":"2020-04-04","cited_by_count":8},{"id":"2204.11205","title":"EPiDA: An Easy Plug-in Data Augmentation Framework for High Performance Text Classification","created":"2022-04-24","cited_by_count":7},{"id":"2205.03071","title":"KECP: Knowledge Enhanced Contrastive Prompting for Few-shot Extractive Question Answering","created":"2022-05-06","cited_by_count":6},{"id":"2203.12000","title":"Text Transformations in Contrastive Self-Supervised Learning: A Review","created":"2022-03-22","cited_by_count":5}],"next_cursor":null}