{"list":"other","total":78,"rows":[{"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":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"1810.02244","title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","created":"2018-10-04","cited_by_count":881},{"id":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"1910.11856","title":"On the Cross-lingual Transferability of Monolingual Representations","created":"2019-10-25","cited_by_count":578},{"id":"2005.00052","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","created":"2020-04-30","cited_by_count":445},{"id":"2003.06713","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","created":"2020-03-14","cited_by_count":376},{"id":"1911.03894","title":"CamemBERT: a Tasty French Language Model","created":"2019-11-10","cited_by_count":368},{"id":"2110.00976","title":"LexGLUE: A Benchmark Dataset for Legal Language Understanding in English","created":"2021-10-03","cited_by_count":310},{"id":"2002.01680","title":"MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding","created":"2020-02-05","cited_by_count":304},{"id":"2112.10668","title":"Few-shot Learning with Multilingual Language Models","created":"2021-12-20","cited_by_count":278},{"id":"2004.13922","title":"Revisiting Pre-Trained Models for Chinese Natural Language Processing","created":"2020-04-29","cited_by_count":266},{"id":"1611.04230","title":"SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents","created":"2016-11-14","cited_by_count":246},{"id":"2012.15828","title":"MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers","created":"2020-12-31","cited_by_count":245},{"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":"1710.06481","title":"Constructing Datasets for Multi-hop Reading Comprehension Across Documents","created":"2017-10-17","cited_by_count":190},{"id":"2112.10684","title":"Efficient Large Scale Language Modeling with Mixtures of Experts","created":"2021-12-20","cited_by_count":175},{"id":"2110.01799","title":"ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts","created":"2021-10-05","cited_by_count":148},{"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":"1711.08611","title":"A Deep Relevance Matching Model for Ad-hoc Retrieval","created":"2017-11-23","cited_by_count":126},{"id":"2105.03887","title":"Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents","created":"2021-05-09","cited_by_count":116},{"id":"2010.02559","title":"LEGAL-BERT: The Muppets straight out of Law School","created":"2020-10-06","cited_by_count":111},{"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":"2105.00572","title":"Larger-Scale Transformers for Multilingual Masked Language Modeling","created":"2021-05-02","cited_by_count":87},{"id":"2105.13562","title":"ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation","created":"2021-05-28","cited_by_count":78},{"id":"1904.07094","title":"CEDR: Contextualized Embeddings for Document Ranking","created":"2019-04-15","cited_by_count":77},{"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":"1805.01217","title":"CLAUDETTE: an Automated Detector of Potentially Unfair Clauses in Online Terms of Service","created":"2018-05-03","cited_by_count":73},{"id":"2302.06100","title":"Can GPT-3 Perform Statutory Reasoning?","created":"2023-02-13","cited_by_count":73},{"id":"2110.08499","title":"PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization","created":"2021-10-16","cited_by_count":62},{"id":"2110.00806","title":"Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark","created":"2021-10-02","cited_by_count":60},{"id":"2203.07228","title":"FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing","created":"2022-03-14","cited_by_count":49},{"id":"2009.08712","title":"The birth of Romanian BERT","created":"2020-09-18","cited_by_count":44},{"id":"2010.01653","title":"An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labels","created":"2020-10-04","cited_by_count":44},{"id":"2108.11792","title":"A Statutory Article Retrieval Dataset in French","created":"2021-08-26","cited_by_count":40},{"id":"2210.13448","title":"EUR-Lex-Sum: A Multi- and Cross-lingual Dataset for Long-form Summarization in the Legal Domain","created":"2022-10-24","cited_by_count":40},{"id":"2008.12014","title":"GREEK-BERT: The Greeks visiting Sesame Street","created":"2020-08-27","cited_by_count":38},{"id":"2010.02557","title":"PolicyQA: A Reading Comprehension Dataset for Privacy Policies","created":"2020-10-06","cited_by_count":34},{"id":"2008.09159","title":"Privacy Policies over Time: Curation and Analysis of a Million-Document Dataset","created":"2020-08-20","cited_by_count":28},{"id":"2105.02751","title":"On the Ethical Limits of Natural Language Processing on Legal Text","created":"2021-05-06","cited_by_count":26},{"id":"1905.02851","title":"FAQ Retrieval using Query-Question Similarity and BERT-Based Query-Answer Relevance","created":"2019-05-08","cited_by_count":25},{"id":"2210.13836","title":"Deconfounding Legal Judgment Prediction for European Court of Human Rights Cases Towards Better Alignment with Experts","created":"2022-10-25","cited_by_count":24},{"id":"2112.14731","title":"LeSICiN: A Heterogeneous Graph-based Approach for Automatic Legal Statute Identification from Indian Legal Documents","created":"2021-12-29","cited_by_count":23},{"id":"2207.04182","title":"Explainable Legal Case Matching via Inverse Optimal Transport-based Rationale Extraction","created":"2022-07-09","cited_by_count":21},{"id":"2105.07903","title":"Factoring Statutory Reasoning as Language Understanding Challenges","created":"2021-05-17","cited_by_count":20},{"id":"2211.00974","title":"Processing Long Legal Documents with Pre-trained Transformers: Modding LegalBERT and Longformer","created":"2022-11-02","cited_by_count":20},{"id":"2005.13342","title":"Towards an Open Platform for Legal Information","created":"2020-05-27","cited_by_count":19},{"id":"2101.00123","title":"Intent Classification and Slot Filling for Privacy Policies","created":"2021-01-01","cited_by_count":19},{"id":"1706.06636","title":"Word-Entity Duet Representations for Document Ranking","created":"2017-06-20","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":"2104.09420","title":"Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis","created":"2021-04-19","cited_by_count":14},{"id":"2110.01485","title":"JuriBERT: A Masked-Language Model Adaptation for French Legal Text","created":"2021-10-04","cited_by_count":14},{"id":"2101.10726","title":"Regulatory Compliance through Doc2Doc Information Retrieval: A case study in EU/UK legislation where text similarity has limitations","created":"2021-01-26","cited_by_count":13},{"id":"2012.03619","title":"Structural Text Segmentation of Legal Documents","created":"2020-12-07","cited_by_count":11},{"id":"2112.07882","title":"Lex Rosetta: Transfer of Predictive Models Across Languages, Jurisdictions, and Legal Domains","created":"2021-12-15","cited_by_count":11},{"id":"2006.08671","title":"To Pretrain or Not to Pretrain: Examining the Benefits of Pretraining on Resource Rich Tasks","created":"2020-06-15","cited_by_count":10},{"id":"2007.03225","title":"Hier-SPCNet: A Legal Statute Hierarchy-based Heterogeneous Network for Computing Legal Case Document Similarity","created":"2020-07-07","cited_by_count":10},{"id":"2112.07165","title":"Discovering Explanatory Sentences in Legal Case Decisions Using Pre-trained Language Models","created":"2021-12-14","cited_by_count":9},{"id":"2301.12847","title":"Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networks","created":"2023-01-30","cited_by_count":9},{"id":"1708.04439","title":"Extractive Summarization using Deep Learning","created":"2017-08-15","cited_by_count":8},{"id":"1905.10348","title":"Predicting Brazilian court decisions","created":"2019-04-20","cited_by_count":8},{"id":"2108.01139","title":"PyEuroVoc: A Tool for Multilingual Legal Document Classification with EuroVoc Descriptors","created":"2021-08-02","cited_by_count":6},{"id":"2110.15709","title":"LegalNLP -- Natural Language Processing methods for the Brazilian Legal Language","created":"2021-10-05","cited_by_count":6},{"id":"2112.03033","title":"Unsupervised Law Article Mining based on Deep Pre-Trained Language Representation Models with Application to the Italian Civil Code","created":"2021-12-02","cited_by_count":6},{"id":"2212.10011","title":"PLUE: Language Understanding Evaluation Benchmark for Privacy Policies in English","created":"2022-12-20","cited_by_count":5},{"id":"2104.13841","title":"Evaluating Document Representations for Content-based Legal Literature Recommendations","created":"2021-04-28","cited_by_count":4},{"id":"2110.01295","title":"SPaR.txt, a cheap Shallow Parsing approach for Regulatory texts","created":"2021-10-04","cited_by_count":2},{"id":"2203.06224","title":"verBERT: Automating Brazilian Case Law Document Multi-label Categorization Using BERT","created":"2022-03-11","cited_by_count":1}],"next_cursor":null}