{
 "id": "SEACrowd/qed",
 "owner": "SEACrowd",
 "name": "qed",
 "downloads": 78,
 "likes": 0,
 "last_modified": "2024-06-24T13:24:19.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "machine-translation",
  "self-supervised-pretraining"
 ],
 "citation": "@inproceedings{abdelali-etal-2014-amara,\n    title = \"The {AMARA} Corpus: Building Parallel Language Resources for the Educational Domain\",\n    author = \"Abdelali, Ahmed  and\n      Guzman, Francisco  and\n      Sajjad, Hassan  and\n      Vogel, Stephan\",\n    editor = \"Calzolari, Nicoletta  and\n      Choukri, Khalid  and\n      Declerck, Thierry  and\n      Loftsson, Hrafn  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 Ninth International Conference on Language Resources and Evaluation ({LREC}'14)\",\n    month = may,\n    year = \"2014\",\n    address = \"Reykjavik, Iceland\",\n    publisher = \"European Language Resources Association (ELRA)\",\n    url = \"http://www.lrec-conf.org/proceedings/lrec2014/pdf/877_Paper.pdf\",\n    pages = \"1856--1862\",\n    abstract = \"This paper presents the AMARA corpus of on-line educational content: a new parallel corpus of educational video subtitles, multilingually aligned for 20 languages, i.e. 20 monolingual corpora and 190 parallel corpora.\n    This corpus includes both resource-rich languages such as English and Arabic, and resource-poor languages such as Hindi and Thai. In this paper, we describe the gathering, validation, and preprocessing of a large collection of parallel,\n    community-generated subtitles. Furthermore, we describe the methodology used to prepare the data for Machine Translation tasks. Additionally, we provide a ",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "edfe95dd190c12b2b74d79728b56b5564edd370a",
 "stated_evidence": "https://huggingface.co/datasets/SEACrowd/qed/blob/edfe95dd190c12b2b74d79728b56b5564edd370a/README.md",
 "file_evidence": "https://huggingface.co/datasets/SEACrowd/qed/blob/edfe95dd190c12b2b74d79728b56b5564edd370a/LICENSE",
 "card_nc": false
}