{
 "id": "ahelk/ccaligned_multilingual",
 "owner": "ahelk",
 "name": "ccaligned_multilingual",
 "downloads": 224,
 "likes": 11,
 "last_modified": "2024-01-18T11:02:11.000Z",
 "stated_licence": "unknown",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "other"
 ],
 "citation": "@inproceedings{elkishky_ccaligned_2020,\n author = {El-Kishky, Ahmed and Chaudhary, Vishrav and Guzm{\\'a}n, Francisco and Koehn, Philipp},\n booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)},\n month = {November},\n title = {{CCAligned}: A Massive Collection of Cross-lingual Web-Document Pairs},\n year = {2020}\n address = \"Online\",\n publisher = \"Association for Computational Linguistics\",\n url = \"https://www.aclweb.org/anthology/2020.emnlp-main.480\",\n doi = \"10.18653/v1/2020.emnlp-main.480\",\n pages = \"5960--5969\"\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "732e0c60b22e16ea2fddcf7b10e4eeff64f88caa",
 "stated_evidence": "https://huggingface.co/datasets/ahelk/ccaligned_multilingual/blob/732e0c60b22e16ea2fddcf7b10e4eeff64f88caa/README.md",
 "file_evidence": "https://huggingface.co/datasets/ahelk/ccaligned_multilingual/tree/732e0c60b22e16ea2fddcf7b10e4eeff64f88caa",
 "card_nc": false
}