{
 "id": "Henok/age_dataset",
 "owner": "Henok",
 "name": "age_dataset",
 "downloads": 76,
 "likes": 2,
 "last_modified": "2024-10-15T05:43:10.000Z",
 "stated_licence": "cc",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "translation"
 ],
 "citation": "@inproceedings{ademtew-birbo-2024-age,\n    title = \"{AGE}: {A}mharic, {G}e{'}ez and {E}nglish Parallel Dataset\",\n    author = \"Ademtew, Henok  and\n      Birbo, Mikiyas\",\n    editor = \"Ojha, Atul Kr.  and\n      Liu, Chao-hong  and\n      Vylomova, Ekaterina  and\n      Pirinen, Flammie  and\n      Abbott, Jade  and\n      Washington, Jonathan  and\n      Oco, Nathaniel  and\n      Malykh, Valentin  and\n      Logacheva, Varvara  and\n      Zhao, Xiaobing\",\n    booktitle = \"Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)\",\n    month = aug,\n    year = \"2024\",\n    address = \"Bangkok, Thailand\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2024.loresmt-1.14\",\n    doi = \"10.18653/v1/2024.loresmt-1.14\",\n    pages = \"139--145\",\n    abstract = \"African languages are not well-represented in Natural Language Processing (NLP). The main reason is a lack of resources for training models. Low-resource languages, such as Amharic and Ge{'}ez, cannot benefit from modern NLP methods because of the lack of high-quality datasets. This paper presents AGE, an open-source tripartite alignment of Amharic, Ge{'}ez, and English parallel dataset. Additionally, we introduced a novel, 1,000 Ge{'}ez-centered sentences sourced from areas such as news and novels. Furthermore, we developed a model from a multilingual pre-trained language model, which brings 12.29 and 30.66 for English-Ge{'}ez and G",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "b7a3fe4472ba9719a4d895308bdc1c136a924418",
 "stated_evidence": "https://huggingface.co/datasets/Henok/age_dataset/blob/b7a3fe4472ba9719a4d895308bdc1c136a924418/README.md",
 "file_evidence": "https://huggingface.co/datasets/Henok/age_dataset/tree/b7a3fe4472ba9719a4d895308bdc1c136a924418",
 "card_nc": false
}