{
 "id": "ai4bharat/samanantar",
 "owner": "ai4bharat",
 "name": "samanantar",
 "downloads": 2607,
 "likes": 48,
 "last_modified": "2024-12-24T08:13:04.000Z",
 "stated_licence": "cc-by-nc-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "translation"
 ],
 "citation": "@article{10.1162/tacl_a_00452,\n    author = {Ramesh, Gowtham and Doddapaneni, Sumanth and Bheemaraj, Aravinth and Jobanputra, Mayank and AK, Raghavan and Sharma, Ajitesh and Sahoo, Sujit and Diddee, Harshita and J, Mahalakshmi and Kakwani, Divyanshu and Kumar, Navneet and Pradeep, Aswin and Nagaraj, Srihari and Deepak, Kumar and Raghavan, Vivek and Kunchukuttan, Anoop and Kumar, Pratyush and Khapra, Mitesh Shantadevi},\n    title = \"{Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages}\",\n    journal = {Transactions of the Association for Computational Linguistics},\n    volume = {10},\n    pages = {145-162},\n    year = {2022},\n    month = {02},\n    abstract = \"{We present Samanantar, the largest publicly available parallel corpora collection for Indic languages. The collection contains a total of 49.7 million sentence pairs between English and 11 Indic languages (from two language families). Specifically, we compile 12.4 million sentence pairs from existing, publicly available parallel corpora, and additionally mine 37.4 million sentence pairs from the Web, resulting in a 4× increase. We mine the parallel sentences from the Web by combining many corpora, tools, and methods: (a) Web-crawled monolingual corpora, (b) document OCR for extracting sentences from scanned documents, (c) multilingual representation models for aligning sentences, and (d) approximate nearest neighbor search for searching in a large collection of sentences. Human ev",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-4.0) is classified as having use restrictions.",
 "revision": "ead34c5b22a0354d350e7dfdd6aece7df5a48f37",
 "stated_evidence": "https://huggingface.co/datasets/ai4bharat/samanantar/blob/ead34c5b22a0354d350e7dfdd6aece7df5a48f37/README.md",
 "file_evidence": "https://huggingface.co/datasets/ai4bharat/samanantar/tree/ead34c5b22a0354d350e7dfdd6aece7df5a48f37",
 "card_nc": false
}