@inproceedings{semenov-etal-2025-findings,
    title = "Findings of the {WMT}25 Terminology Translation Task: Terminology is Useful Especially for Good {MT}s",
    author = "Semenov, Kirill  and
      Huang, Xu  and
      Zouhar, Vil{\'e}m  and
      Berger, Nathaniel  and
      Zhu, Dawei  and
      Oncevay, Arturo  and
      Chen, Pinzhen",
    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-1.30/",
    pages = "554--576",
    ISBN = "979-8-89176-341-8",
    abstract = "The WMT25 Terminology Translation Task releases new resources in high-stakes domains and investigates the capabilities of translation systems to accurately and consistently translate specialized terms. This year, we feature new domain and language coverage over previous editions, introducing two distinct tracks: (1) sentence-level translation in the information technology domain for English{\textrightarrow}German, English{\textrightarrow}Russian, and English{\textrightarrow}Spanish, and (2) document-level translation in the finance domain for English{\ensuremath{\leftrightarrow}}Traditional Chinese with a document-level one-to-many dictionary. Participants are challenged to translate texts under three modes: no terminology, proper terminology, and random terminology, allowing for a causal analysis of terminology utility. Evaluation combines overall quality, terminology accuracy, and terminology consistency. This shared task attracted broad participation, with 13 teams submitting 20 systems in Track 1 and 4 teams participating in Track 2. The results show that providing proper terminology consistently boosts both overall translation quality and term accuracy, whereas reliance on random terminology yields smaller gains. Despite the near-saturation of sentence-level benchmarks, document-level finance translation still fallsshort, indicating an urgent need for long-form evaluation and more robust metrics tailored to professional domains."
}