{
 "id": "rileykim/MMDoc",
 "owner": "rileykim",
 "name": "MMDoc",
 "downloads": 195,
 "likes": 3,
 "last_modified": "2025-12-22T16:15:38.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "image-to-text"
 ],
 "citation": "@dataset{mmdoc_2025,\r\n  title={MMDoc: Multilingual Multimodal Document Translation Dataset},\r\n  author={Seonok Kim},\r\n  year={2025},\r\n  url={https://huggingface.co/datasets/rileykim/MMDoc},\r\n  note={Multilingual Multimodal Document (MMDoc) translation dataset with OCR and multilingual translations. Extended from PATIMT-Bench (https://github.com/XMUDeepLIT/PATIMT-Bench) for multilingual document translation research.}\r\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "5dd5a79d5ff15e7d519fd523c7e5e8949b6e867a",
 "stated_evidence": "https://huggingface.co/datasets/rileykim/MMDoc/blob/5dd5a79d5ff15e7d519fd523c7e5e8949b6e867a/README.md",
 "file_evidence": "https://huggingface.co/datasets/rileykim/MMDoc/tree/5dd5a79d5ff15e7d519fd523c7e5e8949b6e867a",
 "card_nc": false
}