Hugo Laurençon, Lucile Saulnier, Thomas Wang, Christopher Akiki, Albert Villanova del Moral, Teven Le Scao, Leandro von Werra, Chenghao Mou, Eduardo González Ponferrada, Huu Nguyen, Jörg Frohberg, Mario Sasko, Quentin Lhoest, Angelina McMillan-Major, Gérard Dupont, Stella Biderman, Anna Rogers, Loubna Ben Allal, Francesco De Toni, Giada Pistilli, Olivier Nguyen, Somaieh Nikpoor, Maraim Masoud, Pierre Colombo, Javier de la Rosa, Paulo Villegas, Tristan Thrush, Shayne Longpre, Sebastian Nagel 0005, Leon Weber, Manuel Muñoz, Jian Zhu, Daniel van Strien, Zaid Alyafeai, Khalid Almubarak, Minh Chien Vu, Itziar Gonzalez-Dios, Aitor Soroa, Kyle Lo, Manan Dey, Pedro Ortiz Suarez, Aaron Gokaslan, Shamik Bose, David Ifeoluwa Adelani, Long Phan, Hieu Tran, Ian Yu, Suhas Pai, Jenny Chim, Violette Lepercq, Suzana Ilic, Margaret Mitchell, Alexandra Sasha Luccioni, Yacine Jernite. The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset. In Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, A. Oh, editors, Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022. 2022. [doi]
@inproceedings{LaurenconSWAMSW22,
title = {The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset},
author = {Hugo Laurençon and Lucile Saulnier and Thomas Wang and Christopher Akiki and Albert Villanova del Moral and Teven Le Scao and Leandro von Werra and Chenghao Mou and Eduardo González Ponferrada and Huu Nguyen and Jörg Frohberg and Mario Sasko and Quentin Lhoest and Angelina McMillan-Major and Gérard Dupont and Stella Biderman and Anna Rogers and Loubna Ben Allal and Francesco De Toni and Giada Pistilli and Olivier Nguyen and Somaieh Nikpoor and Maraim Masoud and Pierre Colombo and Javier de la Rosa and Paulo Villegas and Tristan Thrush and Shayne Longpre and Sebastian Nagel 0005 and Leon Weber and Manuel Muñoz and Jian Zhu and Daniel van Strien and Zaid Alyafeai and Khalid Almubarak and Minh Chien Vu and Itziar Gonzalez-Dios and Aitor Soroa and Kyle Lo and Manan Dey and Pedro Ortiz Suarez and Aaron Gokaslan and Shamik Bose and David Ifeoluwa Adelani and Long Phan and Hieu Tran and Ian Yu and Suhas Pai and Jenny Chim and Violette Lepercq and Suzana Ilic and Margaret Mitchell and Alexandra Sasha Luccioni and Yacine Jernite},
year = {2022},
url = {http://papers.nips.cc/paper_files/paper/2022/hash/ce9e92e3de2372a4b93353eb7f3dc0bd-Abstract-Datasets_and_Benchmarks.html},
researchr = {https://researchr.org/publication/LaurenconSWAMSW22},
cites = {0},
citedby = {0},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022},
editor = {Sanmi Koyejo and S. Mohamed and A. Agarwal and Danielle Belgrave and K. Cho and A. Oh},
isbn = {9781713871088},
}