@inproceedings{maxim-2026-script,
    title = "Script Correction and Synthetic Pivoting: Adapting Tencent {HY}-{MT} for Low-Resource {T}urkic Translation",
    author = "Maxim, Bolgov",
    editor = "Ojha, Atul Kr.  and
      Liu, Chao-hong  and
      Vylomova, Ekaterina  and
      Pirinen, Flammie  and
      Washington, Jonathan  and
      Oco, Nathaniel  and
      Zhao, Xiaobing",
    booktitle = "Proceedings for the Ninth Workshop on Technologies for Machine Translation of Low Resource Languages ({L}o{R}es{MT} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.loresmt-1.20/",
    pages = "217--221",
    ISBN = "979-8-89176-366-1",
    abstract = "This paper describes a submission to the LoResMT 2026 Shared Task for the Russian-Kazakh, Russian-Bashkir, and English-Chuvash tracks. The primary approach involves parameter-efficient fine-tuning (LoRA) of the Tencent HY-MT1.5-7B multilingual model. For the Russian-Kazakh and Russian-Bashkir pairs, LoRA adaptation was employed to correct the model{'}s default Arabic script output to Cyrillic. For the extremely low-resource English-Chuvash pair, two strategies were compared: mixed training on authentic English-Chuvash and Russian-Chuvash data versus training exclusively on a synthetic English-Chuvash corpus created via pivoting through Russian. Baseline systems included NLLB 1.3B (distilled) for Russian-Kazakh and Russian-Bashkir, and Gemma 2 3B for English-Chuvash. Results demonstrate that adapting a strong multilingual backbone with LoRA yields significant improvements over baselines while successfully addressing script mismatch challenges. Code for training and inference is released at: https://github.com/defdet/low-resource-langs-mt-adapt"
}