{
 "id": "ngwgsang/ViSP",
 "owner": "ngwgsang",
 "name": "ViSP",
 "downloads": 228,
 "likes": 6,
 "last_modified": "2025-05-04T11:51:15.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@inproceedings{nguyen-nguyen-2025-large,\n    title = \"A Large-Scale Benchmark for {V}ietnamese Sentence Paraphrases\",\n    author = \"Nguyen, Sang Quang  and\n      Nguyen, Kiet Van\",\n    editor = \"Chiruzzo, Luis  and\n      Ritter, Alan  and\n      Wang, Lu\",\n    booktitle = \"Findings of the Association for Computational Linguistics: NAACL 2025\",\n    month = apr,\n    year = \"2025\",\n    address = \"Albuquerque, New Mexico\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.findings-naacl.59/\",\n    pages = \"1045--1060\",\n    ISBN = \"979-8-89176-195-7\",\n    abstract = \"This paper presents ViSP, a high-quality Vietnamese dataset for sentence paraphrasing, consisting of 1.2M original{--}paraphrase pairs collected from various domains. The dataset was constructed using a hybrid approach that combines automatic paraphrase generation with manual evaluation to ensure high quality. We conducted experiments using methods such as back-translation, EDA, and baseline models like BART and T5, as well as large language models (LLMs), including GPT-4o, Gemini-1.5, Aya, Qwen-2.5, and Meta-Llama-3.1 variants. To the best of our knowledge, this is the first large-scale study on Vietnamese paraphrasing. We hope that our dataset and findings will serve as a valuable foundation for future research and applications in Vietnamese paraphrase tasks. The dataset is available for research purposes at \\url{https://github.com/ngwgsang/ViSP}.\"\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "79b8edafb9e422330a3cfc663eb8bc2756e3ecf9",
 "stated_evidence": "https://huggingface.co/datasets/ngwgsang/ViSP/blob/79b8edafb9e422330a3cfc663eb8bc2756e3ecf9/README.md",
 "file_evidence": "https://huggingface.co/datasets/ngwgsang/ViSP/tree/79b8edafb9e422330a3cfc663eb8bc2756e3ecf9",
 "card_nc": false
}