@inproceedings{bennett-etal-2025-evaluating,
    title = "Evaluating Evaluation Metrics for {A}ncient {C}hinese to {E}nglish Machine Translation",
    author = "Bennett, Eric R.  and
      Han, HyoJung  and
      Yang, Xinchen  and
      Schonebaum, Andrew  and
      Carpuat, Marine",
    editor = "Anderson, Adam  and
      Gordin, Shai  and
      Li, Bin  and
      Liu, Yudong  and
      Passarotti, Marco C.  and
      Sprugnoli, Rachele",
    booktitle = "Proceedings of the Second Workshop on Ancient Language Processing",
    month = may,
    year = "2025",
    address = "The Albuquerque Convention Center, Laguna",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.alp-1.9/",
    pages = "71--76",
    ISBN = "979-8-89176-235-0",
    abstract = "Evaluation metrics are an important driver of progress in Machine Translation (MT), but they have been primarily validated on high-resource modern languages. In this paper, we conduct an empirical evaluation of metrics commonly used to evaluate MT from Ancient Chinese into English. Using LLMs, we construct a contrastive test set, pairing high-quality MT and purposefully flawed MT of the same Pre-Qin texts. We then evaluate the ability of each metric to discriminate between accurate and flawed translations."
}