{
 "id": "SEACrowd/kopi_cc",
 "owner": "SEACrowd",
 "name": "kopi_cc",
 "downloads": 60,
 "likes": 0,
 "last_modified": "2024-06-24T13:30:00.000Z",
 "stated_licence": null,
 "stated_from": "none",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "self-supervised-pretraining"
 ],
 "citation": "@ARTICLE{2022arXiv220106642A,\n       author = {{Abadji}, Julien and {Ortiz Suarez}, Pedro and {Romary}, Laurent and {Sagot}, Benoit},\n        title = \"{Towards a Cleaner Document-Oriented Multilingual Crawled Corpus}\",\n      journal = {arXiv e-prints},\n     keywords = {Computer Science - Computation and Language},\n         year = 2022,\n        month = jan,\n          eid = {arXiv:2201.06642},\n        pages = {arXiv:2201.06642},\narchivePrefix = {arXiv},\n       eprint = {2201.06642},\n primaryClass = {cs.CL},\n       adsurl = {https://ui.adsabs.harvard.edu/abs/2022arXiv220106642A},\n      adsnote = {Provided by the SAO/NASA Astrophysics Data System}\n}\n@inproceedings{AbadjiOrtizSuarezRomaryetal.2021,\n  author    = {Julien Abadji and Pedro Javier Ortiz Su{'a}rez and Laurent Romary and Benoit Sagot},\n  title     = {Ungoliant: An optimized pipeline for the generation of a very large-scale multilingual web corpus},\n  series = {Proceedings of the Workshop on Challenges in the Management of Large Corpora (CMLC-9) 2021. Limerick, 12 July 2021 (Online-Event)},\n  editor    = {Harald L{\"u}ngen and Marc Kupietz and Piotr Bański and Adrien Barbaresi and Simon Clematide and Ines Pisetta},\n  publisher = {Leibniz-Institut f{\"u}r Deutsche Sprache},\n  address   = {Mannheim},\n  doi       = {10.14618/ids-pub-10468},\n  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-104688},\n  pages     = {1 -- 9},\n  year      = {2021},\n  abstract  = {Since the introduction of large language models in Natura",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "541613c4ebede19ea59b00de651120b520281e32",
 "stated_evidence": "https://huggingface.co/datasets/SEACrowd/kopi_cc/blob/541613c4ebede19ea59b00de651120b520281e32/README.md",
 "file_evidence": "https://huggingface.co/datasets/SEACrowd/kopi_cc/blob/541613c4ebede19ea59b00de651120b520281e32/LICENSE",
 "card_nc": false
}