{"list":"other","total":60,"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":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"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":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"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":"2003.11080","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","created":"2020-03-24","cited_by_count":742},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"1911.03894","title":"CamemBERT: a Tasty French Language Model","created":"2019-11-10","cited_by_count":368},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"2110.00976","title":"LexGLUE: A Benchmark Dataset for Legal Language Understanding in English","created":"2021-10-03","cited_by_count":310},{"id":"1906.05474","title":"Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets","created":"2019-06-13","cited_by_count":299},{"id":"2004.05986","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","created":"2020-04-13","cited_by_count":278},{"id":"1906.08230","title":"Evaluating Protein Transfer Learning with TAPE","created":"2019-06-19","cited_by_count":231},{"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":"2010.10906","title":"German's Next Language Model","created":"2020-10-21","cited_by_count":144},{"id":"2004.12158","title":"How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence","created":"2020-04-25","cited_by_count":129},{"id":"1912.07076","title":"Multilingual is not enough: BERT for Finnish","created":"2019-12-15","cited_by_count":119},{"id":"2105.03887","title":"Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents","created":"2021-05-09","cited_by_count":116},{"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":"1912.09582","title":"BERTje: A Dutch BERT Model","created":"2019-12-19","cited_by_count":109},{"id":"2112.01716","title":"Reduced, Reused and Recycled: The Life of a Dataset in Machine Learning Research","created":"2021-12-03","cited_by_count":102},{"id":"2106.08087","title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","created":"2021-06-15","cited_by_count":101},{"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":"2001.06286","title":"RobBERT: a Dutch RoBERTa-based Language Model","created":"2020-01-17","cited_by_count":88},{"id":"2103.13084","title":"Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases","created":"2021-03-24","cited_by_count":77},{"id":"2203.06849","title":"SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities","created":"2022-03-14","cited_by_count":77},{"id":"2208.00748","title":"Efficient Long-Text Understanding with Short-Text Models","created":"2022-08-01","cited_by_count":71},{"id":"2110.00806","title":"Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark","created":"2021-10-02","cited_by_count":60},{"id":"2206.10883","title":"Multi-LexSum: Real-World Summaries of Civil Rights Lawsuits at Multiple Granularities","created":"2022-06-22","cited_by_count":47},{"id":"2009.08712","title":"The birth of Romanian BERT","created":"2020-09-18","cited_by_count":44},{"id":"2206.05224","title":"A Multi-Task Benchmark for Korean Legal Language Understanding and Judgement Prediction","created":"2022-06-10","cited_by_count":44},{"id":"2008.12014","title":"GREEK-BERT: The Greeks visiting Sesame Street","created":"2020-08-27","cited_by_count":38},{"id":"2007.01658","title":"Playing with Words at the National Library of Sweden -- Making a Swedish BERT","created":"2020-07-03","cited_by_count":35},{"id":"2207.06814","title":"BERTIN: Efficient Pre-Training of a Spanish Language Model using Perplexity Sampling","created":"2022-07-14","cited_by_count":30},{"id":"2105.02751","title":"On the Ethical Limits of Natural Language Processing on Legal Text","created":"2021-05-06","cited_by_count":26},{"id":"2103.13031","title":"Czert -- Czech BERT-like Model for Language Representation","created":"2021-03-24","cited_by_count":22},{"id":"2209.06120","title":"LegalBench: Prototyping a Collaborative Benchmark for Legal Reasoning","created":"2022-09-13","cited_by_count":17},{"id":"2211.00582","title":"ClassActionPrediction: A Challenging Benchmark for Legal Judgment Prediction of Class Action Cases in the US","created":"2022-11-01","cited_by_count":17},{"id":"2011.04784","title":"EstBERT: A Pretrained Language-Specific BERT for Estonian","created":"2020-11-09","cited_by_count":16},{"id":"2209.12325","title":"An Empirical Study on Cross-X Transfer for Legal Judgment Prediction","created":"2022-09-25","cited_by_count":16},{"id":"2109.15298","title":"Multi-granular Legal Topic Classification on Greek Legislation","created":"2021-09-30","cited_by_count":15},{"id":"2110.01485","title":"JuriBERT: A Masked-Language Model Adaptation for French Legal Text","created":"2021-10-04","cited_by_count":14},{"id":"2211.17135","title":"BudgetLongformer: Can we Cheaply Pretrain a SotA Legal Language Model From Scratch?","created":"2022-11-30","cited_by_count":13},{"id":"2107.12930","title":"gaBERT -- an Irish Language Model","created":"2021-07-27","cited_by_count":12},{"id":"2109.15254","title":"SlovakBERT: Slovak Masked Language Model","created":"2021-09-30","cited_by_count":11},{"id":"2110.12201","title":"Spanish Legalese Language Model and Corpora","created":"2021-10-23","cited_by_count":11},{"id":"2211.02956","title":"Privacy-Preserving Models for Legal Natural Language Processing","created":"2022-11-05","cited_by_count":10},{"id":"2112.01342","title":"How not to Lie with a Benchmark: Rearranging NLP Leaderboards","created":"2021-12-02","cited_by_count":9},{"id":"1905.10348","title":"Predicting Brazilian court decisions","created":"2019-04-20","cited_by_count":8},{"id":"2210.08284","title":"AraLegal-BERT: A pretrained language model for Arabic Legal text","created":"2022-10-15","cited_by_count":7},{"id":"2212.08204","title":"LegalRelectra: Mixed-domain Language Modeling for Long-range Legal Text Comprehension","created":"2022-12-16","cited_by_count":7}],"next_cursor":null}