@inproceedings{yin-etal-2025-nttsu,
    title = "{NTTSU} at {WMT}2025 General Translation Task",
    author = "Yin, Zhang  and
      Deguchi, Hiroyuki  and
      Azami, Haruto  and
      Ouyang, Guanyu  and
      Buma, Kosei  and
      Fu, Yingyi  and
      Chousa, Katsuki  and
      Utsuro, Takehito",
    editor = "Haddow, Barry  and
      Kocmi, Tom  and
      Koehn, Philipp  and
      Monz, Christof",
    booktitle = "Proceedings of the Tenth Conference on Machine Translation",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.wmt-1.41/",
    pages = "657--665",
    ISBN = "979-8-89176-341-8",
    abstract = "This paper presents the submission of NTTSU for the constrained track of the English{--}Japanese and Japanese{--}Chinese at the WMT2025 general translation task.For each translation direction, we build translation models from a large language model by combining continual pretraining, supervised fine-tuning, and preference optimization based on the translation quality and adequacy.We finally generate translations via context-aware MBR decoding to maximize translation quality and document-level consistency."
}