{
 "id": "LIACC/Emakhuwa-FLORES",
 "owner": "LIACC",
 "name": "Emakhuwa-FLORES",
 "downloads": 107,
 "likes": 0,
 "last_modified": "2024-12-13T11:07:47.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@inproceedings{ali-etal-2024-expanding,\n    title = \"Expanding {FLORES}+ Benchmark for More Low-Resource Settings: {P}ortuguese-Emakhuwa Machine Translation Evaluation\",\n    author = \"Ali, Felermino Dario Mario  and\n      Lopes Cardoso, Henrique  and\n      Sousa-Silva, Rui\",\n    editor = \"Haddow, Barry  and\n      Kocmi, Tom  and\n      Koehn, Philipp  and\n      Monz, Christof\",\n    booktitle = \"Proceedings of the Ninth Conference on Machine Translation\",\n    month = nov,\n    year = \"2024\",\n    address = \"Miami, Florida, USA\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2024.wmt-1.45\",\n    pages = \"579--592\",\n    abstract = \"As part of the Open Language Data Initiative shared tasks, we have expanded the FLORES+ evaluation set to include Emakhuwa, a low-resource language widely spoken in Mozambique. We translated the \\textit{dev} and \\textit{devtest} sets from Portuguese into Emakhuwa, and we detail the translation process and quality assurance measures used. Our methodology involved various quality checks, including post-editing and adequacy assessments. The resulting datasets consist of multiple reference sentences for each source. We present baseline results from training a Neural Machine Translation system and fine-tuning existing multilingual translation models. Our findings suggest that spelling inconsistencies remain a challenge in Emakhuwa. Additionally, the baseline models underperformed on this evaluation set, unders",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "1ae9e4840e447b4d4e488cc4f6456a848180bbac",
 "stated_evidence": "https://huggingface.co/datasets/LIACC/Emakhuwa-FLORES/blob/1ae9e4840e447b4d4e488cc4f6456a848180bbac/README.md",
 "file_evidence": "https://huggingface.co/datasets/LIACC/Emakhuwa-FLORES/tree/1ae9e4840e447b4d4e488cc4f6456a848180bbac",
 "card_nc": false
}