{
 "id": "jknafou/TransCorpus-bio",
 "owner": "jknafou",
 "name": "TransCorpus-bio",
 "downloads": 763,
 "likes": 0,
 "last_modified": "2026-10-26T09:57:47.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "translation",
  "text-generation"
 ],
 "citation": "If you use this corpus, please cite:\n```text\n  @inproceedings{knafou-etal-2025-transbert,\n      title = \"{T}rans{BERT}: A Framework for Synthetic Translation in Domain-Specific Language Modeling\",\n      author = {Knafou, Julien  and\n        Mottin, Luc  and\n        Mottaz, Ana{\\\"i}s  and\n        Flament, Alexandre  and\n        Ruch, Patrick},\n      editor = \"Christodoulopoulos, Christos  and\n        Chakraborty, Tanmoy  and\n        Rose, Carolyn  and\n        Peng, Violet\",\n      booktitle = \"Findings of the Association for Computational Linguistics: EMNLP 2025\",\n      month = nov,\n      year = \"2025\",\n      address = \"Suzhou, China\",\n      publisher = \"Association for Computational Linguistics\",\n      url = \"https://aclanthology.org/2025.findings-emnlp.1053/\",\n      doi = \"10.18653/v1/2025.findings-emnlp.1053\",\n      pages = \"19338--19354\",\n      ISBN = \"979-8-89176-335-7\",\n      abstract = \"The scarcity of non-English language data in specialized domains significantly limits the development of effective Natural Language Processing (NLP) tools. We present TransBERT, a novel framework for pre-training language models using exclusively synthetically translated text, and introduce TransCorpus, a scalable translation toolkit. Focusing on the life sciences domain in French, our approach demonstrates that state-of-the-art performance on various downstream tasks can be achieved solely by leveraging synthetically translated data. We release the TransCorpus toolkit, the TransCorpus-bi",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "8acb700ae506675e90fd909092577b1f4be15b87",
 "stated_evidence": "https://huggingface.co/datasets/jknafou/TransCorpus-bio/blob/8acb700ae506675e90fd909092577b1f4be15b87/README.md",
 "file_evidence": "https://huggingface.co/datasets/jknafou/TransCorpus-bio/tree/8acb700ae506675e90fd909092577b1f4be15b87",
 "card_nc": false
}