{
 "id": "Alienmaster/wikipedia_leipzig_de_2021",
 "owner": "Alienmaster",
 "name": "wikipedia_leipzig_de_2021",
 "downloads": 38,
 "likes": 0,
 "last_modified": "2024-04-18T13:56:34.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{goldhahn-etal-2012-building,\n    title = \"Building Large Monolingual Dictionaries at the {L}eipzig Corpora Collection: From 100 to 200 Languages\",\n    author = \"Goldhahn, Dirk  and\n      Eckart, Thomas  and\n      Quasthoff, Uwe\",\n    editor = \"Calzolari, Nicoletta  and\n      Choukri, Khalid  and\n      Declerck, Thierry  and\n      Do{\\u{g}}an, Mehmet U{\\u{g}}ur  and\n      Maegaard, Bente  and\n      Mariani, Joseph  and\n      Moreno, Asuncion  and\n      Odijk, Jan  and\n      Piperidis, Stelios\",\n    booktitle = \"Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)\",\n    month = may,\n    year = \"2012\",\n    address = \"Istanbul, Turkey\",\n    publisher = \"European Language Resources Association (ELRA)\",\n    url = \"http://www.lrec-conf.org/proceedings/lrec2012/pdf/327_Paper.pdf\",\n    pages = \"759--765\",\n    abstract = \"The Leipzig Corpora Collection offers free online access to 136 monolingual dictionaries enriched with statistical information. In this paper we describe current advances of the project in collecting and processing text data automatically for a large number of languages. Our main interest lies in languages of “low density”, where only few text data exists online. The aim of this approach is to create monolingual dictionaries and statistical information for a high number of new languages and to expand the existing dictionaries, opening up new possibilities for linguistic typology and other research. Focus of",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "13607865e172f3a611c51389bbe77431adade48d",
 "stated_evidence": "https://huggingface.co/datasets/Alienmaster/wikipedia_leipzig_de_2021/blob/13607865e172f3a611c51389bbe77431adade48d/README.md",
 "file_evidence": "https://huggingface.co/datasets/Alienmaster/wikipedia_leipzig_de_2021/tree/13607865e172f3a611c51389bbe77431adade48d",
 "card_nc": false
}