{
 "id": "community-datasets/cawac",
 "owner": "community-datasets",
 "name": "cawac",
 "downloads": 222,
 "likes": 8,
 "last_modified": "2024-01-16T15:50:41.000Z",
 "stated_licence": "cc-by-sa-3.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "fill-mask"
 ],
 "citation": "@inproceedings{DBLP:conf/lrec/LjubesicT14,\n  author    = {Nikola Ljubesic and\n               Antonio Toral},\n  editor    = {Nicoletta Calzolari and\n               Khalid Choukri and\n               Thierry Declerck and\n               Hrafn Loftsson and\n               Bente Maegaard and\n               Joseph Mariani and\n               Asunci{\\'{o}}n Moreno and\n               Jan Odijk and\n               Stelios Piperidis},\n  title     = {caWaC - {A} web corpus of Catalan and its application to language\n               modeling and machine translation},\n  booktitle = {Proceedings of the Ninth International Conference on Language Resources\n               and Evaluation, {LREC} 2014, Reykjavik, Iceland, May 26-31, 2014},\n  pages     = {1728--1732},\n  publisher = {European Language Resources Association {(ELRA)}},\n  year      = {2014},\n  url       = {http://www.lrec-conf.org/proceedings/lrec2014/summaries/841.html},\n  timestamp = {Mon, 19 Aug 2019 15:23:35 +0200},\n  biburl    = {https://dblp.org/rec/conf/lrec/LjubesicT14.bib},\n  bibsource = {dblp computer science bibliography, https://dblp.org}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-3.0) is classified as share-alike.",
 "revision": "7dc6be007333a09f1b5d2474508c43d18551859d",
 "stated_evidence": "https://huggingface.co/datasets/community-datasets/cawac/blob/7dc6be007333a09f1b5d2474508c43d18551859d/README.md",
 "file_evidence": "https://huggingface.co/datasets/community-datasets/cawac/tree/7dc6be007333a09f1b5d2474508c43d18551859d",
 "card_nc": false
}