{
 "id": "MaLA-LM/mala-bilingual-translation-corpus",
 "owner": "MaLA-LM",
 "name": "mala-bilingual-translation-corpus",
 "downloads": 987,
 "likes": 8,
 "last_modified": "2026-10-16T10:48:02.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "translation"
 ],
 "citation": "@inproceedings{ji-etal-2026-data,\n  title     = {Data-Centric Continual Pre-training for 500+ Languages: A New Bilingual Translation Corpus and Multilingual Models},\n  author    = {Ji, Shaoxiong  and\n               Li, Zihao  and\n               Paavola, Jaakko  and\n               Luo, Hengyu  and\n               Tiedemann, J{\\\"o}rg},\n  editor    = {Liakata, Maria  and\n               Moreira, Viviane P.  and\n               Zhang, Jiajun  and\n               Jurgens, David},\n  booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026},\n  month     = jul,\n  year      = {2026},\n  address   = {San Diego, California, United States},\n  publisher = {Association for Computational Linguistics},\n  url       = {https://aclanthology.org/2026.findings-acl.937/},\n  doi       = {10.18653/v1/2026.findings-acl.937},\n  pages     = {18776--18807},\n  isbn      = {979-8-89176-395-1}\n}\n\n@article{ji2024emma500enhancingmassivelymultilingual,\n      title={{EMMA}-500: Enhancing Massively Multilingual Adaptation of Large Language Models}, \n      author={Shaoxiong Ji and Zihao Li and Indraneil Paul and Jaakko Paavola and Peiqin Lin and Pinzhen Chen and Dayyán O'Brien and Hengyu Luo and Hinrich Schütze and Jörg Tiedemann and Barry Haddow},\n      year={2024},\n      journal={arXiv preprint 2409.17892},\n      url={https://arxiv.org/abs/2409.17892}, \n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "813ef9a154fcd010a797300de6a39d7e0b9aaa1f",
 "stated_evidence": "https://huggingface.co/datasets/MaLA-LM/mala-bilingual-translation-corpus/blob/813ef9a154fcd010a797300de6a39d7e0b9aaa1f/README.md",
 "file_evidence": "https://huggingface.co/datasets/MaLA-LM/mala-bilingual-translation-corpus/tree/813ef9a154fcd010a797300de6a39d7e0b9aaa1f",
 "card_nc": false
}