{"list":"other","total":59,"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1607.01759","title":"Bag of Tricks for Efficient Text Classification","created":"2016-07-06","cited_by_count":876},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2003.07082","title":"Stanza: A Python Natural Language Processing Toolkit for Many Human Languages","created":"2020-03-16","cited_by_count":723},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"1804.10959","title":"Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates","created":"2018-04-29","cited_by_count":639},{"id":"2010.11125","title":"Beyond English-Centric Multilingual Machine Translation","created":"2020-10-21","cited_by_count":561},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"1911.00359","title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data","created":"2019-11-01","cited_by_count":548},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"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":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314},{"id":"2004.11867","title":"Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation","created":"2020-04-24","cited_by_count":277},{"id":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","cited_by_count":243},{"id":"2106.15590","title":"The Values Encoded in Machine Learning Research","created":"2021-06-29","cited_by_count":172},{"id":"2010.02353","title":"Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages","created":"2020-10-05","cited_by_count":159},{"id":"2112.12938","title":"Counterfactual Memorization in Neural Language Models","created":"2021-12-24","cited_by_count":156},{"id":"2103.11811","title":"MasakhaNER: Named Entity Recognition for African Languages","created":"2021-03-22","cited_by_count":155},{"id":"2104.05596","title":"Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages","created":"2021-04-12","cited_by_count":136},{"id":"2006.06202","title":"A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages","created":"2020-06-11","cited_by_count":131},{"id":"1812.06469","title":"The Adverse Effects of Code Duplication in Machine Learning Models of Code","created":"2018-12-16","cited_by_count":126},{"id":"2007.02423","title":"Participation is not a Design Fix for Machine Learning","created":"2020-07-05","cited_by_count":111},{"id":"1711.05073","title":"DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications","created":"2017-11-14","cited_by_count":110},{"id":"1905.00075","title":"On the Use of ArXiv as a Dataset","created":"2019-04-30","cited_by_count":103},{"id":"2108.04308","title":"Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Development","created":"2021-08-09","cited_by_count":85},{"id":"1710.02855","title":"The IIT Bombay English-Hindi Parallel Corpus","created":"2017-10-08","cited_by_count":75},{"id":"2107.06955","title":"HTLM: Hyper-Text Pre-Training and Prompting of Language Models","created":"2021-07-14","cited_by_count":58},{"id":"1801.06146","title":"Universal Language Model Fine-tuning for Text Classification","created":"2018-01-18","cited_by_count":52},{"id":"2105.13947","title":"Changing the World by Changing the Data","created":"2021-05-28","cited_by_count":51},{"id":"2105.05241","title":"Addressing \"Documentation Debt\" in Machine Learning Research: A Retrospective Datasheet for BookCorpus","created":"2021-05-11","cited_by_count":47},{"id":"2011.03116","title":"Behavioral Use Licensing for Responsible AI","created":"2020-11-04","cited_by_count":46},{"id":"2005.00085","title":"AI4Bharat-IndicNLP Corpus: Monolingual Corpora and Word Embeddings for Indic Languages","created":"2020-04-30","cited_by_count":44},{"id":"2201.07311","title":"Datasheet for the Pile","created":"2022-01-13","cited_by_count":43},{"id":"1611.04033","title":"1.5 billion words Arabic Corpus","created":"2016-11-12","cited_by_count":35},{"id":"2206.03216","title":"Data Governance in the Age of Large-Scale Data-Driven Language Technology","created":"2022-05-04","cited_by_count":33},{"id":"2105.01774","title":"Envisioning Communities: A Participatory Approach Towards AI for Social Good","created":"2021-05-04","cited_by_count":30},{"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":"2107.07903","title":"Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalan","created":"2021-07-16","cited_by_count":26},{"id":"2110.14566","title":"IndoNLI: A Natural Language Inference Dataset for Indonesian","created":"2021-10-27","cited_by_count":24},{"id":"1911.09339","title":"Emotion Recognition for Vietnamese Social Media Text","created":"2019-11-21","cited_by_count":23},{"id":"1411.6718","title":"LABR: A Large Scale Arabic Sentiment Analysis Benchmark","created":"2014-11-25","cited_by_count":22},{"id":"2110.06744","title":"Masader: Metadata Sourcing for Arabic Text and Speech Data Resources","created":"2021-10-13","cited_by_count":20},{"id":"2007.07691","title":"A Multilingual Parallel Corpora Collection Effort for Indian Languages","created":"2020-07-15","cited_by_count":16},{"id":"1810.05334","title":"IndoSum: A New Benchmark Dataset for Indonesian Text Summarization","created":"2018-10-12","cited_by_count":14},{"id":"2201.10066","title":"Documenting Geographically and Contextually Diverse Data Sources: The BigScience Catalogue of Language Data and Resources","created":"2022-01-25","cited_by_count":11},{"id":"2203.08111","title":"Does Corpus Quality Really Matter for Low-Resource Languages?","created":"2022-03-15","cited_by_count":11},{"id":"1809.03891","title":"Studying the History of the Arabic Language: Language Technology and a Large-Scale Historical Corpus","created":"2018-09-11","cited_by_count":7}],"next_cursor":null}