{
 "id": "SloppyCalculator/SinFoS",
 "owner": "SloppyCalculator",
 "name": "SinFoS",
 "downloads": 40,
 "likes": 4,
 "last_modified": "2026-03-21T11:00:36.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "translation",
  "text-classification"
 ],
 "citation": "```python\n@inproceedings{sofalas-etal-2026-sinfos,\n    title = \"{S}in{F}o{S}: A Parallel Dataset for Translating {S}inhala Figures of Speech\",\n    author = \"Sofalas, Johan Nevin  and\n      Pavithra, Dilushri  and\n      Jayatilleke, Nevidu  and\n      Weerasinghe, Ruvan\",\n    editor = {Ojha, Atul Kr.  and\n      Mititelu, Verginica Barbu  and\n      Constant, Mathieu  and\n      Stoyanova, Ivelina  and\n      Do{\\u{g}}ru{\\\"o}z, A. Seza  and\n      Rademaker, Alexandre},\n    booktitle = \"Proceedings of the 22nd Workshop on Multiword Expressions ({MWE} 2026)\",\n    month = mar,\n    year = \"2026\",\n    address = \"Rabat, Marocco\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2026.mwe-1.2/\",\n    pages = \"8--26\",\n    ISBN = \"979-8-89176-363-0\",\n    abstract = \"Figures of Speech (FOS) consist of multi-word phrases that are deeply intertwined with culture. While Neural Machine Translation (NMT) performs relatively well with the figurative expressions of high-resource languages, it often faces challenges when dealing with low-resource languages like Sinhala due to limited available data. To address this limitation, we introduce a corpus of 2,344 Sinhala figures of speech with cultural and cross-lingual annotations. We examine this dataset to classify the cultural origins of the figures of speech and to identify their cross-lingual equivalents. Additionally, we have developed a binary classifier to differentiate between two types of FOS in the",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "b0232d6151101c40dbcab72ab249adf8a6d92c24",
 "stated_evidence": "https://huggingface.co/datasets/SloppyCalculator/SinFoS/blob/b0232d6151101c40dbcab72ab249adf8a6d92c24/README.md",
 "file_evidence": "https://huggingface.co/datasets/SloppyCalculator/SinFoS/tree/b0232d6151101c40dbcab72ab249adf8a6d92c24",
 "card_nc": false
}