{
 "id": "QuangDuy/unsupervised_data",
 "owner": "QuangDuy",
 "name": "unsupervised_data",
 "downloads": 357,
 "likes": 0,
 "last_modified": "2026-10-21T12:49:55.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "manual",
 "tasks": [
  "sentence-similarity",
  "feature-extraction"
 ],
 "citation": "@misc{duc2024comprehensivevietnameseretrievalaugmentedgeneration,\r\n      title={Towards Comprehensive Vietnamese Retrieval-Augmented Generation and Large Language Models}, \r\n      author={Nguyen Quang Duc and Le Hai Son and Nguyen Duc Nhan and Nguyen Dich Nhat Minh and Le Thanh Huong and Dinh Viet Sang},\r\n      year={2024},\r\n      eprint={2403.01616},\r\n      archivePrefix={arXiv},\r\n      primaryClass={cs.CL},\r\n      url={https://arxiv.org/abs/2403.01616}, \r\n}\r\n\r\n@misc{bajaj2018msmarcohumangenerated,\r\n      title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, \r\n      author={Payal Bajaj and Daniel Campos and Nick Craswell and Li Deng and Jianfeng Gao and Xiaodong Liu and Rangan Majumder and Andrew McNamara and Bhaskar Mitra and Tri Nguyen and Mir Rosenberg and Xia Song and Alina Stoica and Saurabh Tiwary and Tong Wang},\r\n      year={2018},\r\n      eprint={1611.09268},\r\n      archivePrefix={arXiv},\r\n      primaryClass={cs.CL},\r\n      url={https://arxiv.org/abs/1611.09268}, \r\n}\r\n\r\n@misc{vnmteb,\r\n      title={VN-MTEB: Vietnamese Massive Text Embedding Benchmark}, \r\n      author={Loc Pham and Tung Luu and Thu Vo and Minh Nguyen and Viet Hoang},\r\n      year={2025},\r\n      eprint={2507.21500},\r\n      archivePrefix={arXiv},\r\n      primaryClass={cs.CL},\r\n      url={https://arxiv.org/abs/2507.21500}, \r\n}\r\n\r\n@dataset{penedo2025finewiki,\r\n  author    = {Guilherme Penedo},\r\n  title     = {FineWiki},\r\n  year      = {2025},\r\n  publisher = {Hugging Face Datasets},\r\n  url",
 "signal": "restrictive",
 "reason": "The dataset card's licence name or licence section contains wording that suggests non-commercial, research-only or academic-only use restrictions.",
 "revision": "3730d5baa99a0784dabb7c34d510b1b5f844915f",
 "stated_evidence": "https://huggingface.co/datasets/QuangDuy/unsupervised_data/blob/3730d5baa99a0784dabb7c34d510b1b5f844915f/README.md",
 "file_evidence": "https://huggingface.co/datasets/QuangDuy/unsupervised_data/tree/3730d5baa99a0784dabb7c34d510b1b5f844915f",
 "card_nc": true
}