{"list":"other","total":53,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"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":"2104.08821","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","created":"2021-04-18","cited_by_count":2173},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"1904.12848","title":"Unsupervised Data Augmentation for Consistency Training","created":"2019-04-29","cited_by_count":1060},{"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":"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":"1906.03671","title":"Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds","created":"2019-06-09","cited_by_count":610},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"2209.01975","title":"Selective Annotation Makes Language Models Better Few-Shot Learners","created":"2022-09-05","cited_by_count":243},{"id":"2006.05987","title":"Revisiting Few-sample BERT Fine-tuning","created":"2020-06-10","cited_by_count":238},{"id":"1810.00337","title":"Learning to Perform Local Rewriting for Combinatorial Optimization","created":"2018-09-30","cited_by_count":185},{"id":"2108.02035","title":"Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification","created":"2021-08-04","cited_by_count":183},{"id":"2108.04106","title":"Noisy Channel Language Model Prompting for Few-Shot Text Classification","created":"2021-08-09","cited_by_count":165},{"id":"2004.02105","title":"Unsupervised Domain Clusters in Pretrained Language Models","created":"2020-04-05","cited_by_count":160},{"id":"2109.03764","title":"Active Learning by Acquiring Contrastive Examples","created":"2021-09-08","cited_by_count":156},{"id":"2111.01998","title":"OpenPrompt: An Open-source Framework for Prompt-learning","created":"2021-11-03","cited_by_count":148},{"id":"2202.02794","title":"Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets","created":"2022-02-06","cited_by_count":133},{"id":"2010.09535","title":"Cold-start Active Learning through Self-supervised Language Modeling","created":"2020-10-19","cited_by_count":128},{"id":"2108.13161","title":"Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners","created":"2021-08-30","cited_by_count":115},{"id":"2103.11955","title":"Improving and Simplifying Pattern Exploiting Training","created":"2021-03-22","cited_by_count":97},{"id":"2010.02194","title":"Self-training Improves Pre-training for Natural Language Understanding","created":"2020-10-05","cited_by_count":96},{"id":"2010.07835","title":"Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach","created":"2020-10-15","cited_by_count":83},{"id":"2107.07170","title":"FLEX: Unifying Evaluation for Few-Shot NLP","created":"2021-07-15","cited_by_count":67},{"id":"2202.05433","title":"A Survey on Programmatic Weak Supervision","created":"2022-02-11","cited_by_count":66},{"id":"2107.02331","title":"Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering","created":"2021-07-06","cited_by_count":62},{"id":"2107.05687","title":"Revisiting Uncertainty-based Query Strategies for Active Learning with Transformers","created":"2021-07-12","cited_by_count":60},{"id":"2010.02322","title":"SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup","created":"2020-10-05","cited_by_count":52},{"id":"1812.11270","title":"Weakly-Supervised Hierarchical Text Classification","created":"2018-12-29","cited_by_count":42},{"id":"2101.08133","title":"Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates","created":"2021-01-20","cited_by_count":39},{"id":"2104.08320","title":"On the Importance of Effectively Adapting Pretrained Language Models for Active Learning","created":"2021-04-16","cited_by_count":32},{"id":"1802.07427","title":"Active Learning with Partial Feedback","created":"2018-02-21","cited_by_count":27},{"id":"2107.03176","title":"On Training Instance Selection for Few-Shot Neural Text Generation","created":"2021-07-07","cited_by_count":26},{"id":"2109.04282","title":"Cartography Active Learning","created":"2021-09-09","cited_by_count":26},{"id":"2011.14696","title":"On Initial Pools for Deep Active Learning","created":"2020-11-30","cited_by_count":18},{"id":"2004.08046","title":"Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Space","created":"2020-04-17","cited_by_count":17},{"id":"2205.11166","title":"Prompt Tuning for Discriminative Pre-trained Language Models","created":"2022-05-23","cited_by_count":17},{"id":"2203.09735","title":"PRBoost: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning","created":"2022-03-18","cited_by_count":14},{"id":"2203.10581","title":"Cluster & Tune: Boost Cold Start Performance in Text Classification","created":"2022-03-20","cited_by_count":13},{"id":"2104.07611","title":"Adapting Coreference Resolution Models through Active Learning","created":"2021-04-15","cited_by_count":11},{"id":"2204.09347","title":"Active Few-Shot Learning with FASL","created":"2022-04-20","cited_by_count":11},{"id":"2112.07522","title":"LMTurk: Few-Shot Learners as Crowdsourcing Workers in a Language-Model-as-a-Service Framework","created":"2021-12-14","cited_by_count":9},{"id":"2207.12028","title":"Unsupervised data selection for Speech Recognition with contrastive loss ratios","created":"2022-07-25","cited_by_count":7},{"id":"2106.00139","title":"Training ELECTRA Augmented with Multi-word Selection","created":"2021-05-31","cited_by_count":4},{"id":"2107.06703","title":"Zero-Round Active Learning","created":"2021-07-14","cited_by_count":1}],"next_cursor":null}