The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset

The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset. Laurençon, H., Saulnier, L., Wang, T., Akiki, C., del Moral, A. V., Scao, T. L., von Werra, L., Mou, C., Ponferrada, E. G., Nguyen, H., Frohberg, J., Sasko, M., Lhoest, Q., McMillan-Major, A., Dupont, G., Biderman, S., Rogers, A., Allal, L. B., Toni, F. D., Pistilli, G., Nguyen, O., Nikpoor, S., Masoud, M., Colombo, P., de la Rosa, J., Villegas, P., Thrush, T., Longpre, S., Nagel, S., Weber, L., Muñoz, M., Zhu, J., van Strien, D., Alyafeai, Z., Almubarak, K., Vu, M. C., Gonzalez-Dios, I., Soroa, A., Lo, K., Dey, M., Suarez, P. O., Gokaslan, A., Bose, S., Adelani, D. I., Phan, L., Tran, H., Yu, I., Pai, S., Chim, J., Lepercq, V., Ilic, S., Mitchell, M., Luccioni, A. S., & Jernite, Y. In Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., & Oh, A., 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.

Paper bibtex

@inproceedings{DBLP:conf/nips/LaurenconSWAMSW22,
  author       = {Hugo Lauren{\c{c}}on 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 Gonz{\'{a}}lez Ponferrada and
                  Huu Nguyen and
                  J{\"{o}}rg Frohberg and
                  Mario Sasko and
                  Quentin Lhoest and
                  Angelina McMillan{-}Major and
                  G{\'{e}}rard 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 Mu{\~{n}}oz 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},
  editor       = {Sanmi Koyejo and
                  S. Mohamed and
                  A. Agarwal and
                  Danielle Belgrave and
                  K. Cho and
                  A. Oh},
  title        = {The BigScience {ROOTS} Corpus: {A} 1.6TB Composite Multilingual Dataset},
  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},
  year         = {2022},
  url          = {http://papers.nips.cc/paper\_files/paper/2022/hash/ce9e92e3de2372a4b93353eb7f3dc0bd-Abstract-Datasets\_and\_Benchmarks.html},
  timestamp    = {Sat, 13 Jul 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/nips/LaurenconSWAMSW22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

Downloads: 0

{"_id":"ZuZZtpqcmdTYWsKe4","bibbaseid":"laurenon-saulnier-wang-akiki-delmoral-scao-vonwerra-mou-etal-thebigsciencerootscorpusa16tbcompositemultilingualdataset-2022","author_short":["Laurençon, H.","Saulnier, L.","Wang, T.","Akiki, C.","del Moral, A. V.","Scao, T. L.","von Werra, L.","Mou, C.","Ponferrada, E. G.","Nguyen, H.","Frohberg, J.","Sasko, M.","Lhoest, Q.","McMillan-Major, A.","Dupont, G.","Biderman, S.","Rogers, A.","Allal, L. B.","Toni, F. D.","Pistilli, G.","Nguyen, O.","Nikpoor, S.","Masoud, M.","Colombo, P.","de la Rosa, J.","Villegas, P.","Thrush, T.","Longpre, S.","Nagel, S.","Weber, L.","Muñoz, M.","Zhu, J.","van Strien, D.","Alyafeai, Z.","Almubarak, K.","Vu, M. C.","Gonzalez-Dios, I.","Soroa, A.","Lo, K.","Dey, M.","Suarez, P. O.","Gokaslan, A.","Bose, S.","Adelani, D. I.","Phan, L.","Tran, H.","Yu, I.","Pai, S.","Chim, J.","Lepercq, V.","Ilic, S.","Mitchell, M.","Luccioni, A. S.","Jernite, Y."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Hugo"],"propositions":[],"lastnames":["Laurençon"],"suffixes":[]},{"firstnames":["Lucile"],"propositions":[],"lastnames":["Saulnier"],"suffixes":[]},{"firstnames":["Thomas"],"propositions":[],"lastnames":["Wang"],"suffixes":[]},{"firstnames":["Christopher"],"propositions":[],"lastnames":["Akiki"],"suffixes":[]},{"firstnames":["Albert","Villanova"],"propositions":["del"],"lastnames":["Moral"],"suffixes":[]},{"firstnames":["Teven","Le"],"propositions":[],"lastnames":["Scao"],"suffixes":[]},{"firstnames":["Leandro"],"propositions":["von"],"lastnames":["Werra"],"suffixes":[]},{"firstnames":["Chenghao"],"propositions":[],"lastnames":["Mou"],"suffixes":[]},{"firstnames":["Eduardo","González"],"propositions":[],"lastnames":["Ponferrada"],"suffixes":[]},{"firstnames":["Huu"],"propositions":[],"lastnames":["Nguyen"],"suffixes":[]},{"firstnames":["Jörg"],"propositions":[],"lastnames":["Frohberg"],"suffixes":[]},{"firstnames":["Mario"],"propositions":[],"lastnames":["Sasko"],"suffixes":[]},{"firstnames":["Quentin"],"propositions":[],"lastnames":["Lhoest"],"suffixes":[]},{"firstnames":["Angelina"],"propositions":[],"lastnames":["McMillan-Major"],"suffixes":[]},{"firstnames":["Gérard"],"propositions":[],"lastnames":["Dupont"],"suffixes":[]},{"firstnames":["Stella"],"propositions":[],"lastnames":["Biderman"],"suffixes":[]},{"firstnames":["Anna"],"propositions":[],"lastnames":["Rogers"],"suffixes":[]},{"firstnames":["Loubna","Ben"],"propositions":[],"lastnames":["Allal"],"suffixes":[]},{"firstnames":["Francesco","De"],"propositions":[],"lastnames":["Toni"],"suffixes":[]},{"firstnames":["Giada"],"propositions":[],"lastnames":["Pistilli"],"suffixes":[]},{"firstnames":["Olivier"],"propositions":[],"lastnames":["Nguyen"],"suffixes":[]},{"firstnames":["Somaieh"],"propositions":[],"lastnames":["Nikpoor"],"suffixes":[]},{"firstnames":["Maraim"],"propositions":[],"lastnames":["Masoud"],"suffixes":[]},{"firstnames":["Pierre"],"propositions":[],"lastnames":["Colombo"],"suffixes":[]},{"firstnames":["Javier"],"propositions":["de","la"],"lastnames":["Rosa"],"suffixes":[]},{"firstnames":["Paulo"],"propositions":[],"lastnames":["Villegas"],"suffixes":[]},{"firstnames":["Tristan"],"propositions":[],"lastnames":["Thrush"],"suffixes":[]},{"firstnames":["Shayne"],"propositions":[],"lastnames":["Longpre"],"suffixes":[]},{"firstnames":["Sebastian"],"propositions":[],"lastnames":["Nagel"],"suffixes":[]},{"firstnames":["Leon"],"propositions":[],"lastnames":["Weber"],"suffixes":[]},{"firstnames":["Manuel"],"propositions":[],"lastnames":["Muñoz"],"suffixes":[]},{"firstnames":["Jian"],"propositions":[],"lastnames":["Zhu"],"suffixes":[]},{"firstnames":["Daniel"],"propositions":["van"],"lastnames":["Strien"],"suffixes":[]},{"firstnames":["Zaid"],"propositions":[],"lastnames":["Alyafeai"],"suffixes":[]},{"firstnames":["Khalid"],"propositions":[],"lastnames":["Almubarak"],"suffixes":[]},{"firstnames":["Minh","Chien"],"propositions":[],"lastnames":["Vu"],"suffixes":[]},{"firstnames":["Itziar"],"propositions":[],"lastnames":["Gonzalez-Dios"],"suffixes":[]},{"firstnames":["Aitor"],"propositions":[],"lastnames":["Soroa"],"suffixes":[]},{"firstnames":["Kyle"],"propositions":[],"lastnames":["Lo"],"suffixes":[]},{"firstnames":["Manan"],"propositions":[],"lastnames":["Dey"],"suffixes":[]},{"firstnames":["Pedro","Ortiz"],"propositions":[],"lastnames":["Suarez"],"suffixes":[]},{"firstnames":["Aaron"],"propositions":[],"lastnames":["Gokaslan"],"suffixes":[]},{"firstnames":["Shamik"],"propositions":[],"lastnames":["Bose"],"suffixes":[]},{"firstnames":["David","Ifeoluwa"],"propositions":[],"lastnames":["Adelani"],"suffixes":[]},{"firstnames":["Long"],"propositions":[],"lastnames":["Phan"],"suffixes":[]},{"firstnames":["Hieu"],"propositions":[],"lastnames":["Tran"],"suffixes":[]},{"firstnames":["Ian"],"propositions":[],"lastnames":["Yu"],"suffixes":[]},{"firstnames":["Suhas"],"propositions":[],"lastnames":["Pai"],"suffixes":[]},{"firstnames":["Jenny"],"propositions":[],"lastnames":["Chim"],"suffixes":[]},{"firstnames":["Violette"],"propositions":[],"lastnames":["Lepercq"],"suffixes":[]},{"firstnames":["Suzana"],"propositions":[],"lastnames":["Ilic"],"suffixes":[]},{"firstnames":["Margaret"],"propositions":[],"lastnames":["Mitchell"],"suffixes":[]},{"firstnames":["Alexandra","Sasha"],"propositions":[],"lastnames":["Luccioni"],"suffixes":[]},{"firstnames":["Yacine"],"propositions":[],"lastnames":["Jernite"],"suffixes":[]}],"editor":[{"firstnames":["Sanmi"],"propositions":[],"lastnames":["Koyejo"],"suffixes":[]},{"firstnames":["S."],"propositions":[],"lastnames":["Mohamed"],"suffixes":[]},{"firstnames":["A."],"propositions":[],"lastnames":["Agarwal"],"suffixes":[]},{"firstnames":["Danielle"],"propositions":[],"lastnames":["Belgrave"],"suffixes":[]},{"firstnames":["K."],"propositions":[],"lastnames":["Cho"],"suffixes":[]},{"firstnames":["A."],"propositions":[],"lastnames":["Oh"],"suffixes":[]}],"title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","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","year":"2022","url":"http://papers.nips.cc/paper\\_files/paper/2022/hash/ce9e92e3de2372a4b93353eb7f3dc0bd-Abstract-Datasets\\_and\\_Benchmarks.html","timestamp":"Sat, 13 Jul 2024 01:00:00 +0200","biburl":"https://dblp.org/rec/conf/nips/LaurenconSWAMSW22.bib","bibsource":"dblp computer science bibliography, https://dblp.org","bibtex":"@inproceedings{DBLP:conf/nips/LaurenconSWAMSW22,\n author = {Hugo Lauren{\\c{c}}on and\n Lucile Saulnier and\n Thomas Wang and\n Christopher Akiki and\n Albert Villanova del Moral and\n Teven Le Scao and\n Leandro von Werra and\n Chenghao Mou and\n Eduardo Gonz{\\'{a}}lez Ponferrada and\n Huu Nguyen and\n J{\\\"{o}}rg Frohberg and\n Mario Sasko and\n Quentin Lhoest and\n Angelina McMillan{-}Major and\n G{\\'{e}}rard Dupont and\n Stella Biderman and\n Anna Rogers and\n Loubna Ben Allal and\n Francesco De Toni and\n Giada Pistilli and\n Olivier Nguyen and\n Somaieh Nikpoor and\n Maraim Masoud and\n Pierre Colombo and\n Javier de la Rosa and\n Paulo Villegas and\n Tristan Thrush and\n Shayne Longpre and\n Sebastian Nagel and\n Leon Weber and\n Manuel Mu{\\~{n}}oz and\n Jian Zhu and\n Daniel van Strien and\n Zaid Alyafeai and\n Khalid Almubarak and\n Minh Chien Vu and\n Itziar Gonzalez{-}Dios and\n Aitor Soroa and\n Kyle Lo and\n Manan Dey and\n Pedro Ortiz Suarez and\n Aaron Gokaslan and\n Shamik Bose and\n David Ifeoluwa Adelani and\n Long Phan and\n Hieu Tran and\n Ian Yu and\n Suhas Pai and\n Jenny Chim and\n Violette Lepercq and\n Suzana Ilic and\n Margaret Mitchell and\n Alexandra Sasha Luccioni and\n Yacine Jernite},\n editor = {Sanmi Koyejo and\n S. Mohamed and\n A. Agarwal and\n Danielle Belgrave and\n K. Cho and\n A. Oh},\n title = {The BigScience {ROOTS} Corpus: {A} 1.6TB Composite Multilingual Dataset},\n booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference\n on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,\n LA, USA, November 28 - December 9, 2022},\n year = {2022},\n url = {http://papers.nips.cc/paper\\_files/paper/2022/hash/ce9e92e3de2372a4b93353eb7f3dc0bd-Abstract-Datasets\\_and\\_Benchmarks.html},\n timestamp = {Sat, 13 Jul 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/conf/nips/LaurenconSWAMSW22.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n","author_short":["Laurençon, H.","Saulnier, L.","Wang, T.","Akiki, C.","del Moral, A. V.","Scao, T. L.","von Werra, L.","Mou, C.","Ponferrada, E. G.","Nguyen, H.","Frohberg, J.","Sasko, M.","Lhoest, Q.","McMillan-Major, A.","Dupont, G.","Biderman, S.","Rogers, A.","Allal, L. B.","Toni, F. D.","Pistilli, G.","Nguyen, O.","Nikpoor, S.","Masoud, M.","Colombo, P.","de la Rosa, J.","Villegas, P.","Thrush, T.","Longpre, S.","Nagel, S.","Weber, L.","Muñoz, M.","Zhu, J.","van Strien, D.","Alyafeai, Z.","Almubarak, K.","Vu, M. C.","Gonzalez-Dios, I.","Soroa, A.","Lo, K.","Dey, M.","Suarez, P. O.","Gokaslan, A.","Bose, S.","Adelani, D. I.","Phan, L.","Tran, H.","Yu, I.","Pai, S.","Chim, J.","Lepercq, V.","Ilic, S.","Mitchell, M.","Luccioni, A. S.","Jernite, Y."],"editor_short":["Koyejo, S.","Mohamed, S.","Agarwal, A.","Belgrave, D.","Cho, K.","Oh, A."],"key":"DBLP:conf/nips/LaurenconSWAMSW22","id":"DBLP:conf/nips/LaurenconSWAMSW22","bibbaseid":"laurenon-saulnier-wang-akiki-delmoral-scao-vonwerra-mou-etal-thebigsciencerootscorpusa16tbcompositemultilingualdataset-2022","role":"author","urls":{"Paper":"http://papers.nips.cc/paper\\_files/paper/2022/hash/ce9e92e3de2372a4b93353eb7f3dc0bd-Abstract-Datasets\\_and\\_Benchmarks.html"},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://dblp.org/pid/229/3167.bib","dataSources":["FD6yNzHMPC2zrsvYD","GXv5EbWSzjLH96rpE"],"keywords":[],"search_terms":["bigscience","roots","corpus","6tb","composite","multilingual","dataset","laurençon","saulnier","wang","akiki","del moral","scao","von werra","mou","ponferrada","nguyen","frohberg","sasko","lhoest","mcmillan-major","dupont","biderman","rogers","allal","toni","pistilli","nguyen","nikpoor","masoud","colombo","de la rosa","villegas","thrush","longpre","nagel","weber","muñoz","zhu","van strien","alyafeai","almubarak","vu","gonzalez-dios","soroa","lo","dey","suarez","gokaslan","bose","adelani","phan","tran","yu","pai","chim","lepercq","ilic","mitchell","luccioni","jernite"],"title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","year":2022}