{
 "id": "hfxunlp/opus_wikipedia",
 "owner": "hfxunlp",
 "name": "opus_wikipedia",
 "downloads": 10,
 "likes": 0,
 "last_modified": "2026-02-25T11:57:01.000Z",
 "stated_licence": "unknown",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "manual",
 "tasks": [
  "translation"
 ],
 "citation": "@article{WOLK2014126,\ntitle = {Building Subject-aligned Comparable Corpora and Mining it for Truly Parallel Sentence Pairs},\njournal = {Procedia Technology},\nvolume = {18},\npages = {126-132},\nyear = {2014},\nnote = {International workshop on Innovations in Information and Communication Science and Technology, IICST 2014, 3-5 September 2014, Warsaw, Poland},\nissn = {2212-0173},\ndoi = {https://doi.org/10.1016/j.protcy.2014.11.024},\nurl = {https://www.sciencedirect.com/science/article/pii/S2212017314005453},\nauthor = {Krzysztof Wołk and Krzysztof Marasek},\nkeywords = {Comparable corpora, machine translation, NLP},\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "62d615e9f0a3cf8bd0a182c296f0920516f34632",
 "stated_evidence": "https://huggingface.co/datasets/hfxunlp/opus_wikipedia/blob/62d615e9f0a3cf8bd0a182c296f0920516f34632/README.md",
 "file_evidence": "https://huggingface.co/datasets/hfxunlp/opus_wikipedia/tree/62d615e9f0a3cf8bd0a182c296f0920516f34632",
 "card_nc": false
}