{
 "id": "UdS-LSV/menyo20k_mt",
 "owner": "UdS-LSV",
 "name": "menyo20k_mt",
 "downloads": 337,
 "likes": 11,
 "last_modified": "2024-01-18T11:08:52.000Z",
 "stated_licence": "cc-by-nc-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "translation"
 ],
 "citation": "@inproceedings{adelani-etal-2021-effect,\n    title = \"The Effect of Domain and Diacritics in {Y}oruba{--}{E}nglish Neural Machine Translation\",\n    author = \"Adelani, David  and\n      Ruiter, Dana  and\n      Alabi, Jesujoba  and\n      Adebonojo, Damilola  and\n      Ayeni, Adesina  and\n      Adeyemi, Mofe  and\n      Awokoya, Ayodele Esther  and\n      Espa{\\~n}a-Bonet, Cristina\",\n    booktitle = \"Proceedings of the 18th Biennial Machine Translation Summit (Volume 1: Research Track)\",\n    month = aug,\n    year = \"2021\",\n    address = \"Virtual\",\n    publisher = \"Association for Machine Translation in the Americas\",\n    url = \"https://aclanthology.org/2021.mtsummit-research.6\",\n    pages = \"61--75\",\n    abstract = \"Massively multilingual machine translation (MT) has shown impressive capabilities and including zero and few-shot translation between low-resource language pairs. However and these models are often evaluated on high-resource languages with the assumption that they generalize to low-resource ones. The difficulty of evaluating MT models on low-resource pairs is often due to lack of standardized evaluation datasets. In this paper and we present MENYO-20k and the first multi-domain parallel corpus with a especially curated orthography for Yoruba{--}English with standardized train-test splits for benchmarking. We provide several neural MT benchmarks and compare them to the performance of popular pre-trained (massively multilingual) MT models both for the heterogeneous test s",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-4.0) is classified as having use restrictions.",
 "revision": "76b2db67f218ce7a92da597c01df17031f37a6d0",
 "stated_evidence": "https://huggingface.co/datasets/UdS-LSV/menyo20k_mt/blob/76b2db67f218ce7a92da597c01df17031f37a6d0/README.md",
 "file_evidence": "https://huggingface.co/datasets/UdS-LSV/menyo20k_mt/tree/76b2db67f218ce7a92da597c01df17031f37a6d0",
 "card_nc": false
}