{"list":"other","total":53,"rows":[{"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":"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":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1901.08746","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","created":"2019-01-25","cited_by_count":1947},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"1904.03323","title":"Publicly Available Clinical BERT Embeddings","created":"2019-04-06","cited_by_count":1002},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"1312.6184","title":"Do Deep Nets Really Need to be Deep?","created":"2013-12-21","cited_by_count":474},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"2110.00976","title":"LexGLUE: A Benchmark Dataset for Legal Language Understanding in English","created":"2021-10-03","cited_by_count":310},{"id":"1910.06188","title":"Q8BERT: Quantized 8Bit BERT","created":"2019-10-14","cited_by_count":300},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242},{"id":"2104.08671","title":"When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset","created":"2021-04-18","cited_by_count":201},{"id":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177},{"id":"2110.01799","title":"ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts","created":"2021-10-05","cited_by_count":148},{"id":"2004.07320","title":"Training with Quantization Noise for Extreme Model Compression","created":"2020-04-15","cited_by_count":145},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141},{"id":"1908.08962","title":"Well-Read Students Learn Better: On the Importance of Pre-training Compact Models","created":"2019-08-23","cited_by_count":120},{"id":"2005.00561","title":"When BERT Plays the Lottery, All Tickets Are Winning","created":"2020-05-01","cited_by_count":114},{"id":"2207.00220","title":"Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset","created":"2022-07-01","cited_by_count":113},{"id":"2206.05229","title":"Measuring the Carbon Intensity of AI in Cloud Instances","created":"2022-06-10","cited_by_count":111},{"id":"1811.04017","title":"A generic framework for privacy preserving deep learning","created":"2018-11-09","cited_by_count":103},{"id":"2109.00904","title":"MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer","created":"2021-09-02","cited_by_count":90},{"id":"1802.04730","title":"Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions","created":"2018-02-13","cited_by_count":85},{"id":"1906.00532","title":"Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model","created":"2019-06-03","cited_by_count":59},{"id":"2203.06482","title":"FiNER: Financial Numeric Entity Recognition for XBRL Tagging","created":"2022-03-12","cited_by_count":50},{"id":"2002.03794","title":"The Deep Learning Compiler: A Comprehensive Survey","created":"2020-02-06","cited_by_count":46},{"id":"2208.06178","title":"Mining Legal Arguments in Court Decisions","created":"2022-08-12","cited_by_count":35},{"id":"2203.07856","title":"Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Setting","created":"2022-03-15","cited_by_count":23},{"id":"1805.12096","title":"Marian: Cost-effective High-Quality Neural Machine Translation in C++","created":"2018-05-30","cited_by_count":22},{"id":"2209.14389","title":"Downstream Datasets Make Surprisingly Good Pretraining Corpora","created":"2022-09-28","cited_by_count":20},{"id":"1805.03871","title":"Obligation and Prohibition Extraction Using Hierarchical RNNs","created":"2018-05-10","cited_by_count":18},{"id":"2208.08140","title":"Differential Privacy in Natural Language Processing: The Story So Far","created":"2022-08-17","cited_by_count":12},{"id":"2203.15996","title":"TextPruner: A Model Pruning Toolkit for Pre-Trained Language Models","created":"2022-03-30","cited_by_count":10},{"id":"2206.03785","title":"Realistic Zero-Shot Cross-Lingual Transfer in Legal Topic Classification","created":"2022-06-08","cited_by_count":4}],"next_cursor":null}