{"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"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":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"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":"1704.03976","title":"Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning","created":"2017-04-13","cited_by_count":920},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"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":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"1711.10160","title":"Snorkel: Rapid Training Data Creation with Weak Supervision","created":"2017-11-28","cited_by_count":372},{"id":"1904.12584","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","created":"2019-04-26","cited_by_count":372},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"1711.11157","title":"A Semantic Loss Function for Deep Learning with Symbolic Knowledge","created":"2017-11-29","cited_by_count":270},{"id":"1912.01412","title":"Deep Learning for Symbolic Mathematics","created":"2019-12-02","cited_by_count":270},{"id":"2002.05867","title":"Transformers as Soft Reasoners over Language","created":"2020-02-14","cited_by_count":270},{"id":"2109.00725","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","created":"2021-09-02","cited_by_count":178},{"id":"1909.03004","title":"Show Your Work: Improved Reporting of Experimental Results","created":"2019-09-06","cited_by_count":169},{"id":"2010.12884","title":"NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints","created":"2020-10-24","cited_by_count":149},{"id":"1904.01608","title":"Structural Scaffolds for Citation Intent Classification in Scientific Publications","created":"2019-04-02","cited_by_count":130},{"id":"2108.13161","title":"Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners","created":"2021-08-30","cited_by_count":115},{"id":"2104.07143","title":"An Interpretability Illusion for BERT","created":"2021-04-14","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":"2109.11377","title":"WRENCH: A Comprehensive Benchmark for Weak Supervision","created":"2021-09-23","cited_by_count":96},{"id":"1412.6632","title":"Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)","created":"2014-12-20","cited_by_count":94},{"id":"1606.05464","title":"Stance Detection with Bidirectional Conditional Encoding","created":"2016-06-17","cited_by_count":93},{"id":"1808.00508","title":"Neural Arithmetic Logic Units","created":"2018-08-01","cited_by_count":70},{"id":"2004.06025","title":"Learning from Rules Generalizing Labeled Exemplars","created":"2020-04-13","cited_by_count":59},{"id":"2012.06046","title":"Interactive Weak Supervision: Learning Useful Heuristics for Data Labeling","created":"2020-12-11","cited_by_count":52},{"id":"2104.05514","title":"Self-Training with Weak Supervision","created":"2021-04-12","cited_by_count":49},{"id":"2107.07498","title":"FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark","created":"2021-07-15","cited_by_count":41},{"id":"2109.06270","title":"STraTA: Self-Training with Task Augmentation for Better Few-shot Learning","created":"2021-09-13","cited_by_count":33},{"id":"2109.13006","title":"RuleBert: Teaching Soft Rules to Pre-trained Language Models","created":"2021-09-24","cited_by_count":25},{"id":"2109.04727","title":"A Simple and Effective Method To Eliminate the Self Language Bias in Multilingual Representations","created":"2021-09-10","cited_by_count":17},{"id":"2008.09887","title":"Semi-Supervised Data Programming with Subset Selection","created":"2020-08-22","cited_by_count":16},{"id":"2106.07804","title":"Controlling Neural Networks with Rule Representations","created":"2021-06-14","cited_by_count":16},{"id":"2005.06133","title":"Adaptive Rule Discovery for Labeling Text Data","created":"2020-05-13","cited_by_count":15},{"id":"2105.12848","title":"BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition","created":"2021-05-26","cited_by_count":15},{"id":"2109.11410","title":"Learning to Robustly Aggregate Labeling Functions for Semi-supervised Data Programming","created":"2021-09-23","cited_by_count":11},{"id":"2112.01342","title":"How not to Lie with a Benchmark: Rearranging NLP Leaderboards","created":"2021-12-02","cited_by_count":9},{"id":"2107.13077","title":"Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation","created":"2021-07-27","cited_by_count":4},{"id":"1905.09103","title":"Neural-Symbolic Argumentation Mining: an Argument in Favor of Deep Learning and Reasoning","created":"2019-05-22","cited_by_count":3}],"next_cursor":null}