@inproceedings{mino-etal-2025-nhk,
    title = "{NHK} Submission to {WAT} 2025: Leveraging Preference Optimization for Article-level {J}apanese{--}{E}nglish News Translation",
    author = "Mino, Hideya  and
      Endo, Rei  and
      Kawai, Yoshihiko",
    editor = "Nakazawa, Toshiaki  and
      Goto, Isao",
    booktitle = "Proceedings of the Twelfth Workshop on Asian Translation (WAT 2025)",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.wat-1.9/",
    pages = "98--102",
    ISBN = "979-8-89176-309-8",
    abstract = "This paper describes our submission to the Japanese $\rightarrow$ English Article-level News Translation Task at WAT 2025. In this task, participants were provided with a small but high-quality parallel corpus along with two intermediate English translations: a literal translation and a style-adapted translation. To effectively exploit these limited training data, our system employs a large language model (LLM) trained via supervised fine-tuning (SFT) followed by Direct Preference Optimization (DPO) that is a preference learning technique for aligning model outputs with professional-quality references. By leveraging literal and style-adapted intermediate translations as negative (rejected) samples and human-edited English articles as positive (chosen) samples in DPO training, we achieved notable improvements in translation quality. We evaluate our approach using BLEU scores and human assessments."
}