@article{thebigsciencerootscorpusa16tbcomposite, 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 Šaško and Quentin Lhoest and Angelina McMillan-Major and Gerard 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 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 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 Sasha Alexandra Luccioni and Yacine Jernite}, year = {2023}, eprint = {2303.03915}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2303.03915v1}, }