@inproceedings{doi-etal-2026-simul,
    title = "Simul-{COMET}: A Quality Metric for Simultaneous Interpretation in Distant Language Pair Considering Word Order Difference",
    author = "Doi, Kosuke  and
      Makinae, Mana  and
      Sakai, Yusuke  and
      Kamigaito, Hidetaka  and
      Watanabe, Taro",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.2110/",
    pages = "42515--42533",
    ISBN = "979-8-89176-395-1",
    abstract = "In simultaneous interpretation (SI), interpreters perform real-time translation by segmenting the source speech into chunks and translating them in the order they appear.Since surface-matching metrics such as BLEU correlate poorly with human evaluations, translation quality is often evaluated using neural metrics that measure semantic similarity, such as COMET.However, while SI translation ideally exhibits high monotonicity, COMET tends to assign higher scores to offline translations with long-distance reordering, because it is trained on such offline translation data.To address this gap, we propose Simul-COMET, a variation of COMET adapted for SI evaluation specifically designed for monotonicity.We train Simul-COMET on the SI-style translation data, which was converted from the offline translation of the COMET training data by leveraging large language models.In English{--}Japanese translation experiments, we demonstrate that Simul-COMET assigns higher scores to SI-style translations than to offline ones.Moreover, Simul-COMET shows stronger alignment with evaluation scores provided by professional interpreters than the original COMET.Simul-COMET is available at https://github.com/kosuked/simul-comet."
}