{
 "id": "LIACC/Emakhuwa-News-Topic-Classification",
 "owner": "LIACC",
 "name": "Emakhuwa-News-Topic-Classification",
 "downloads": 111,
 "likes": 0,
 "last_modified": "2024-11-11T16:28:15.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "translation",
  "text-classification"
 ],
 "citation": "@inproceedings{ali-etal-2024-building,\n    title = \"Building Resources for Emakhuwa: Machine Translation and News Classification Benchmarks\",\n    author = \"Ali, Felermino D. M. A.  and\n      Lopes Cardoso, Henrique  and\n      Sousa-Silva, Rui\",\n    editor = \"Al-Onaizan, Yaser  and\n      Bansal, Mohit  and\n      Chen, Yun-Nung\",\n    booktitle = \"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing\",\n    month = nov,\n    year = \"2024\",\n    address = \"Miami, Florida, USA\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2024.emnlp-main.824\",\n    pages = \"14842--14857\",\n    abstract = \"This paper introduces a comprehensive collection of NLP resources for Emakhuwa, Mozambique{'}s most widely spoken language. The resources include the first manually translated news bitext corpus between Portuguese and Emakhuwa, news topic classification datasets, and monolingual data. We detail the process and challenges of acquiring this data and present benchmark results for machine translation and news topic classification tasks. Our evaluation examines the impact of different data types{---}originally clean text, post-corrected OCR, and back-translated data{---}and the effects of fine-tuning from pre-trained models, including those focused on African languages.Our benchmarks demonstrate good performance in news topic classification and promising results in machine translation. We fine-tuned multilingual encoder-d",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "06ee71636c99e78e2d88a08b38fdd3c10bddbe05",
 "stated_evidence": "https://huggingface.co/datasets/LIACC/Emakhuwa-News-Topic-Classification/blob/06ee71636c99e78e2d88a08b38fdd3c10bddbe05/README.md",
 "file_evidence": "https://huggingface.co/datasets/LIACC/Emakhuwa-News-Topic-Classification/tree/06ee71636c99e78e2d88a08b38fdd3c10bddbe05",
 "card_nc": false
}