%0 Conference Paper %1 akiki:2022c %A Laurencon, Hugo %A Saulnier, Lucile %A Wang, Thomas %A Akiki, Christopher %A Moral, Albert Villanova %A Scao, Teven Le %A others, %B Advances in Neural Information Processing Systems 35 (NeurIPS 2022) %D 2022 %E Koyejo, S. %E Mohamed, S. %E Agarwal, A. %E Belgrave, D. %E Cho, K. %E Oh, A. %I Curran Associates, Inc. %K topic_language zno %P 31809-31826 %T The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset %U https://proceedings.neurips.cc/paper_files/paper/2022/file/ce9e92e3de2372a4b93353eb7f3dc0bd-Paper-Datasets_and_Benchmarks.pdf %V 35

@inproceedings{akiki:2022c, added-at = {2024-09-10T11:56:37.000+0200}, author = {Lauren\c{c}on, Hugo and Saulnier, Lucile and Wang, Thomas and Akiki, Christopher and Moral, Albert Villanova and Scao, Teven Le and others}, biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/2465a54b7bfc80855418913d786017b39/scadsfct}, booktitle = {Advances in Neural Information Processing Systems 35 (NeurIPS 2022)}, editor = {Koyejo, S. and Mohamed, S. and Agarwal, A. and Belgrave, D. and Cho, K. and Oh, A.}, interhash = {d30b9b60948bb07e4faafc77c8dff311}, intrahash = {465a54b7bfc80855418913d786017b39}, keywords = {topic_language zno}, month = dec, pages = {31809-31826}, publisher = {Curran Associates, Inc.}, timestamp = {2025-07-29T10:29:15.000+0200}, title = {{The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset}}, url = {https://proceedings.neurips.cc/paper_files/paper/2022/file/ce9e92e3de2372a4b93353eb7f3dc0bd-Paper-Datasets_and_Benchmarks.pdf}, volume = 35, year = 2022 }