@inproceedings{lin-etal-2025-scarcity,
    title = "From Scarcity to Scalability: Lexicon and Grammar Enhanced {A}mis to {M}andarin Translation with {GPT} Models",
    author = "Lin, Joseph  and
      Lin, Kai-Ying  and
      Kao, Hung-Yu",
    editor = "Chang, Kai-Wei  and
      Lu, Ke-Han  and
      Yang, Chih-Kai  and
      Tam, Zhi-Rui  and
      Chang, Wen-Yu  and
      Wang, Chung-Che",
    booktitle = "Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)",
    month = nov,
    year = "2025",
    address = "National Taiwan University, Taipei City, Taiwan",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/dashboard/2025.rocling-main.20/",
    pages = "167--175",
    ISBN = "979-8-89176-379-1",
    abstract = "Machine translation (MT) for low-resource languages remains constrained by extreme data scarcity, making traditional fine-tuning infeasible. This study examines Amis{\textrightarrow}Mandarin translation as a practical case, leveraging GPT-4o-mini and GPT-5-mini with dictionary integration and grammar-informed prompting. Experiments show that GPT-5-mini, supported by dictionary, achieves usable quality (BLEU-3 {\ensuremath{\sim}}31, COMET {\ensuremath{\sim}}78, BLEURT {\ensuremath{\sim}}71). To address the bottleneck of incomplete dictionaries, we propose Context-Driven Lexical Augmentation, which infers Mandarin equivalents for unseen Amis terms from corpus context, raising BLEU-3 to 34 and establishing a stronger basis for semi-automatic corpus generation. These results demonstrate that expanding and refining dictionary provides greater benefits than parameter-intensive fine-tuning in extremely low-resource settings. We also discuss the performance gap between Amis{\textrightarrow}Mandarin and Mandarin{\textrightarrow}Amis translation, attributing it to Amis{'}s morphological complexity and narrower semantic coverage. Overall, our resource-driven strategy offers a scalable pathway toward high-quality MT and corpus expansion, ultimately supporting both linguistic research and language revitalization."
}