{
 "id": "coastalcph/tydi_xor_rc",
 "owner": "coastalcph",
 "name": "tydi_xor_rc",
 "downloads": 2504,
 "likes": 0,
 "last_modified": "2025-10-17T08:01:26.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [
  {
   "id": "wikipedia",
   "licence": "cc-by-sa-3.0",
   "found": true,
   "evidence": "https://huggingface.co/datasets/legacy-datasets/wikipedia/blob/97a0b052c326b45fb68593a14972d9eed884cd17/README.md"
  }
 ],
 "gated": false,
 "tasks": [
  "question-answering"
 ],
 "citation": "@article{clark-etal-2020-tydi,\n    title = \"{T}y{D}i {QA}: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages\",\n    author = \"Clark, Jonathan H.  and\n      Choi, Eunsol  and\n      Collins, Michael  and\n      Garrette, Dan  and\n      Kwiatkowski, Tom  and\n      Nikolaev, Vitaly  and\n      Palomaki, Jennimaria\",\n    editor = \"Johnson, Mark  and\n      Roark, Brian  and\n      Nenkova, Ani\",\n    journal = \"Transactions of the Association for Computational Linguistics\",\n    volume = \"8\",\n    year = \"2020\",\n    address = \"Cambridge, MA\",\n    publisher = \"MIT Press\",\n    url = \"https://aclanthology.org/2020.tacl-1.30\",\n    doi = \"10.1162/tacl_a_00317\",\n    pages = \"454--470\",\n    abstract = \"Confidently making progress on multilingual modeling requires challenging, trustworthy evaluations. We present TyDi QA{---}a question answering dataset covering 11 typologically diverse languages with 204K question-answer pairs. The languages of TyDi QA are diverse with regard to their typology{---}the set of linguistic features each language expresses{---}such that we expect models performing well on this set to generalize across a large number of the world{'}s languages. We present a quantitative analysis of the data quality and example-level qualitative linguistic analyses of observed language phenomena that would not be found in English-only corpora. To provide a realistic information-seeking task and avoid priming effects, questions are written by peopl",
 "signal": "conflict",
 "reason": "The declared licence (mit) may conflict with a source dataset's reported share-alike licence (cc-by-sa-3.0).",
 "revision": "d991050dc758461db19dc918bf7cbdad34f52a7e",
 "stated_evidence": "https://huggingface.co/datasets/coastalcph/tydi_xor_rc/blob/d991050dc758461db19dc918bf7cbdad34f52a7e/README.md",
 "file_evidence": "https://huggingface.co/datasets/coastalcph/tydi_xor_rc/tree/d991050dc758461db19dc918bf7cbdad34f52a7e",
 "card_nc": false
}