{"list":"other","total":63,"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":"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":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"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":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1904.12848","title":"Unsupervised Data Augmentation for Consistency Training","created":"2019-04-29","cited_by_count":1060},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"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":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"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":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2002.06305","title":"Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping","created":"2020-02-15","cited_by_count":384},{"id":"2104.06599","title":"Learning How to Ask: Querying LMs with Mixtures of Soft Prompts","created":"2021-04-14","cited_by_count":377},{"id":"1808.09121","title":"WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations","created":"2018-08-28","cited_by_count":372},{"id":"2302.03668","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","created":"2023-02-07","cited_by_count":336},{"id":"2104.05240","title":"Factual Probing Is [MASK]: Learning vs. Learning to Recall","created":"2021-04-12","cited_by_count":291},{"id":"2010.15980","title":"AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts","created":"2020-10-29","cited_by_count":249},{"id":"2105.11259","title":"PTR: Prompt Tuning with Rules for Text Classification","created":"2021-05-24","cited_by_count":238},{"id":"2101.00121","title":"WARP: Word-level Adversarial ReProgramming","created":"2021-01-01","cited_by_count":221},{"id":"1810.12885","title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension","created":"2018-10-30","cited_by_count":200},{"id":"1909.00505","title":"Commonsense Knowledge Mining from Pretrained Models","created":"2019-09-02","cited_by_count":189},{"id":"1911.03118","title":"Not Enough Data? Deep Learning to the Rescue!","created":"2019-11-08","cited_by_count":175},{"id":"1904.01608","title":"Structural Scaffolds for Citation Intent Classification in Scientific Publications","created":"2019-04-02","cited_by_count":130},{"id":"2104.04670","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","created":"2021-04-10","cited_by_count":128},{"id":"1905.08941","title":"Augmenting Data with Mixup for Sentence Classification: An Empirical Study","created":"2019-05-22","cited_by_count":125},{"id":"1710.06071","title":"PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts","created":"2017-10-17","cited_by_count":124},{"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":"2012.11926","title":"Few-Shot Text Generation with Pattern-Exploiting Training","created":"2020-12-22","cited_by_count":87},{"id":"2103.05327","title":"BERTese: Learning to Speak to BERT","created":"2021-03-09","cited_by_count":82},{"id":"2110.01852","title":"Data Augmentation Approaches in Natural Language Processing: A Survey","created":"2021-10-05","cited_by_count":82},{"id":"2006.11834","title":"AdvAug: Robust Adversarial Augmentation for Neural Machine Translation","created":"2020-06-21","cited_by_count":67},{"id":"2102.12206","title":"PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains","created":"2021-02-24","cited_by_count":61},{"id":"2202.12499","title":"PromDA: Prompt-based Data Augmentation for Low-Resource NLU Tasks","created":"2022-02-25","cited_by_count":51},{"id":"1910.12795","title":"Learning Data Manipulation for Augmentation and Weighting","created":"2019-10-28","cited_by_count":45},{"id":"2205.14704","title":"Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning","created":"2022-05-29","cited_by_count":36},{"id":"2108.06332","title":"FlipDA: Effective and Robust Data Augmentation for Few-Shot Learning","created":"2021-08-13","cited_by_count":32},{"id":"2210.14169","title":"Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding","created":"2022-10-25","cited_by_count":32},{"id":"2203.12258","title":"Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View","created":"2022-03-23","cited_by_count":31},{"id":"2202.00535","title":"Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning","created":"2022-02-01","cited_by_count":25},{"id":"2212.02216","title":"Improving Few-Shot Performance of Language Models via Nearest Neighbor Calibration","created":"2022-12-05","cited_by_count":24},{"id":"2109.03685","title":"Open Aspect Target Sentiment Classification with Natural Language Prompts","created":"2021-09-08","cited_by_count":20},{"id":"2203.07781","title":"UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQL","created":"2022-03-15","cited_by_count":20},{"id":"2109.00523","title":"Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification","created":"2021-09-01","cited_by_count":15},{"id":"2210.14803","title":"Don't Prompt, Search! Mining-based Zero-Shot Learning with Language Models","created":"2022-10-26","cited_by_count":13},{"id":"2009.08138","title":"FewJoint: A Few-shot Learning Benchmark for Joint Language Understanding","created":"2020-09-17","cited_by_count":10},{"id":"2205.09229","title":"PromptDA: Label-guided Data Augmentation for Prompt-based Few-shot Learners","created":"2022-05-18","cited_by_count":7},{"id":"2212.00192","title":"Towards Practical Few-shot Federated NLP","created":"2022-12-01","cited_by_count":5}],"next_cursor":null}