{
 "id": "ltrciiith/The-LTRC-Hindi-Telugu-Parallel-Corpus",
 "owner": "ltrciiith",
 "name": "The-LTRC-Hindi-Telugu-Parallel-Corpus",
 "downloads": 8,
 "likes": 2,
 "last_modified": "2024-12-06T02:37:53.000Z",
 "stated_licence": "cc-by-nc-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "auto",
 "tasks": [],
 "citation": "@inproceedings{mujadia-sharma-2022-ltrc,\n    title = \"The {LTRC} {H}indi-{T}elugu Parallel Corpus\",\n    author = \"Mujadia, Vandan  and\n      Sharma, Dipti\",\n    editor = \"Calzolari, Nicoletta  and\n      B{\\'e}chet, Fr{\\'e}d{\\'e}ric  and\n      Blache, Philippe  and\n      Choukri, Khalid  and\n      Cieri, Christopher  and\n      Declerck, Thierry  and\n      Goggi, Sara  and\n      Isahara, Hitoshi  and\n      Maegaard, Bente  and\n      Mariani, Joseph  and\n      Mazo, H{\\'e}l{\\`e}ne  and\n      Odijk, Jan  and\n      Piperidis, Stelios\",\n    booktitle = \"Proceedings of the Thirteenth Language Resources and Evaluation Conference\",\n    month = jun,\n    year = \"2022\",\n    address = \"Marseille, France\",\n    publisher = \"European Language Resources Association\",\n    url = \"https://aclanthology.org/2022.lrec-1.365\",\n    pages = \"3417--3424\",\n    abstract = \"We present the Hindi-Telugu Parallel Corpus of different technical domains such as Natural Science, Computer Science, Law and Healthcare along with the General domain. The qualitative corpus consists of 700K parallel sentences of which 535K sentences were created using multiple methods such as extract, align and review of Hindi-Telugu corpora, end-to-end human translation, iterative back-translation driven post-editing and around 165K parallel sentences were collected from available sources in the public domain. We present the comparative assessment of created parallel corpora for representativeness and diversity. The corpus has been p",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-4.0) is classified as having use restrictions.",
 "revision": "cc62c16dc83c34ad17f18db9ddebb0d63b6209c5",
 "stated_evidence": "https://huggingface.co/datasets/ltrciiith/The-LTRC-Hindi-Telugu-Parallel-Corpus/blob/cc62c16dc83c34ad17f18db9ddebb0d63b6209c5/README.md",
 "file_evidence": "https://huggingface.co/datasets/ltrciiith/The-LTRC-Hindi-Telugu-Parallel-Corpus/tree/cc62c16dc83c34ad17f18db9ddebb0d63b6209c5",
 "card_nc": false
}