{
 "id": "uctnlp/t2x",
 "owner": "uctnlp",
 "name": "t2x",
 "downloads": 48,
 "likes": 0,
 "last_modified": "2026-08-18T13:12:59.000Z",
 "stated_licence": "cc-by-nc-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@inproceedings{meyer-buys-2024-triples,\n    title = \"Triples-to-isi{X}hosa ({T}2{X}): Addressing the Challenges of Low-Resource Agglutinative Data-to-Text Generation\",\n    author = \"Meyer, Francois  and\n      Buys, Jan\",\n    editor = \"Calzolari, Nicoletta  and\n      Kan, Min-Yen  and\n      Hoste, Veronique  and\n      Lenci, Alessandro  and\n      Sakti, Sakriani  and\n      Xue, Nianwen\",\n    booktitle = \"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)\",\n    month = may,\n    year = \"2024\",\n    address = \"Torino, Italia\",\n    publisher = \"ELRA and ICCL\",\n    url = \"https://aclanthology.org/2024.lrec-main.1464/\",\n    pages = \"16841--16854\",\n    abstract = \"Most data-to-text datasets are for English, so the difficulties of modelling data-to-text for low-resource languages are largely unexplored. In this paper we tackle data-to-text for isiXhosa, which is low-resource and agglutinative. We introduce Triples-to-isiXhosa (T2X), a new dataset based on a subset of WebNLG, which presents a new linguistic context that shifts modelling demands to subword-driven techniques. We also develop an evaluation framework for T2X that measures how accurately generated text describes the data. This enables future users of T2X to go beyond surface-level metrics in evaluation. On the modelling side we explore two classes of methods - dedicated data-to-text models trained from scratch and pretrained language model",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-sa-4.0) is classified as having use restrictions.",
 "revision": "d4d06e415f72b1e4616ceb4d785ed0dfec41fc32",
 "stated_evidence": "https://huggingface.co/datasets/uctnlp/t2x/blob/d4d06e415f72b1e4616ceb4d785ed0dfec41fc32/README.md",
 "file_evidence": "https://huggingface.co/datasets/uctnlp/t2x/tree/d4d06e415f72b1e4616ceb4d785ed0dfec41fc32",
 "card_nc": false
}