{
 "id": "ukr-detect/ukr-formality-dataset-seminatural",
 "owner": "ukr-detect",
 "name": "ukr-formality-dataset-seminatural",
 "downloads": 8,
 "likes": 0,
 "last_modified": "2025-02-03T19:37:52.000Z",
 "stated_licence": "openrail++",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{dementieva-etal-2025-cross,\n    title = \"Cross-lingual Text Classification Transfer: The Case of {U}krainian\",\n    author = \"Dementieva, Daryna  and\n      Khylenko, Valeriia  and\n      Groh, Georg\",\n    editor = \"Rambow, Owen  and\n      Wanner, Leo  and\n      Apidianaki, Marianna  and\n      Al-Khalifa, Hend  and\n      Eugenio, Barbara Di  and\n      Schockaert, Steven\",\n    booktitle = \"Proceedings of the 31st International Conference on Computational Linguistics\",\n    month = jan,\n    year = \"2025\",\n    address = \"Abu Dhabi, UAE\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.coling-main.97/\",\n    pages = \"1451--1464\",\n    abstract = \"Despite the extensive amount of labeled datasets in the NLP text classification field, the persistent imbalance in data availability across various languages remains evident. To support further fair development of NLP models, exploring the possibilities of effective knowledge transfer to new languages is crucial. Ukrainian, in particular, stands as a language that still can benefit from the continued refinement of cross-lingual methodologies. Due to our knowledge, there is a tremendous lack of Ukrainian corpora for typical text classification tasks, i.e., different types of style, or harmful speech, or texts relationships. However, the amount of resources required for such corpora collection from scratch is understandable. In this work, we leverage the state-of-the-art advanc",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "2bac3df1c922643c0ca99edd4e565ece2bd0c7e7",
 "stated_evidence": "https://huggingface.co/datasets/ukr-detect/ukr-formality-dataset-seminatural/blob/2bac3df1c922643c0ca99edd4e565ece2bd0c7e7/README.md",
 "file_evidence": "https://huggingface.co/datasets/ukr-detect/ukr-formality-dataset-seminatural/tree/2bac3df1c922643c0ca99edd4e565ece2bd0c7e7",
 "card_nc": false
}