{
 "id": "PredictiveManish/multilingual-corpus",
 "owner": "PredictiveManish",
 "name": "multilingual-corpus",
 "downloads": 123,
 "likes": 1,
 "last_modified": "2026-02-01T12:08:28.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [
  {
   "id": "ai4bharat/samanantar",
   "licence": "cc-by-nc-4.0",
   "found": true,
   "evidence": "https://huggingface.co/datasets/ai4bharat/samanantar/blob/ead34c5b22a0354d350e7dfdd6aece7df5a48f37/README.md"
  }
 ],
 "gated": false,
 "tasks": [
  "text-generation",
  "translation"
 ],
 "citation": "@inproceedings{samanantar_2021,\n  title = {Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages},\n  author = {Gowtham Ramesh and Sumanth Doddapaneni and Aravinth Bheemaraj and Mayank Jobanputra and Raghavan AK and Ajitesh Sharma and Sujit Sahoo and Harshita Diddee and Mahalakshmi J and Divyanshu Kakwani and Navneet Kumar and Aswin Pradeep and Srihari Nagaraj and Kumar Deepak and Vivek Raghavan and Anoop Kunchukuttan and Pratyush Kumar and Mitesh Shantadevi Khapra},\n  booktitle = {Proceedings of the Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks},\n  year = {2021},\n  url = {https://arxiv.org/abs/2104.05596}\n}",
 "signal": "conflict",
 "reason": "The declared licence (cc-by-4.0) may conflict with a source dataset's reported licence (cc-by-nc-4.0), which is classified as having use restrictions.",
 "revision": "4477834f39aa334b822890c990c8d038cc2b8326",
 "stated_evidence": "https://huggingface.co/datasets/PredictiveManish/multilingual-corpus/blob/4477834f39aa334b822890c990c8d038cc2b8326/README.md",
 "file_evidence": "https://huggingface.co/datasets/PredictiveManish/multilingual-corpus/tree/4477834f39aa334b822890c990c8d038cc2b8326",
 "card_nc": false
}