{
 "id": "MLRS/korpus_malti",
 "owner": "MLRS",
 "name": "korpus_malti",
 "downloads": 123,
 "likes": 8,
 "last_modified": "2025-11-11T09:13:36.000Z",
 "stated_licence": "cc-by-nc-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "auto",
 "tasks": [
  "text-generation",
  "fill-mask"
 ],
 "citation": "@inproceedings{BERTu,\n    title = \"Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and {BERT} Models for {M}altese\",\n    author = \"Micallef, Kurt  and\n              Gatt, Albert  and\n              Tanti, Marc  and\n              van der Plas, Lonneke  and\n              Borg, Claudia\",\n    booktitle = \"Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing\",\n    month = jul,\n    year = \"2022\",\n    address = \"Hybrid\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2022.deeplo-1.10\",\n    doi = \"10.18653/v1/2022.deeplo-1.10\",\n    pages = \"90--101\",\n}",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-sa-4.0) is classified as having use restrictions.",
 "revision": "0d4deed0444aadaa1b24585fdb57216aa7003457",
 "stated_evidence": "https://huggingface.co/datasets/MLRS/korpus_malti/blob/0d4deed0444aadaa1b24585fdb57216aa7003457/README.md",
 "file_evidence": "https://huggingface.co/datasets/MLRS/korpus_malti/tree/0d4deed0444aadaa1b24585fdb57216aa7003457",
 "card_nc": false
}