@InProceedings{charkiewicz-EtAl:2026:wmt,
  author    = {Charkiewicz, Adrian  and  Chen, Pinzhen  and  Etchegoyhen, Thierry  and  Gete, Harritxu  and  Guttmann, Kamil  and  Huang, Xu  and  Ponce, David  and  Nowakowski, Artur  and  Odermatt, Frederic  and  Oncevay, Arturo  and  Zhu, Dawei  and  Zouhar, Vilem  and  Semenov, Kirill},
  title     = {Findings of the WMT26 Terminology Translation Task: The Hard Part is Finding the Terms, Not Using Them},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {1053--1086},
  abstract  = {The WMT26 Terminology Translation Task aims to evaluate machine translation in high-stakes, term-heavy domains (technology, finance, medicine). This year, we focus solely on document-level translation and run two tasks: (1) MT with explicit document-level dictionaries, (2) MT with bitext samples that contain the specific terms. Participants are presented with the texts in three translation directions, two of which feature mid-to-low-resourced morphologically rich languages: Spanish${\rightarrow}$Basque, English${\rightarrow}$Polish, and Traditional Chinese${\rightarrow}$English. This year, the main metrics were multiple variants of overall translation quality and terminology success rate; in line with previous shared tasks, we also compared systems with no terminology, proper dictionaries, and random dictionaries to causally analyze terminology utility. 17 teams participated in our task, submitting 21 systems to Track 1 and 18 systems to Track 2. The results show that document-level translation with explicit dictionaries is close to saturation, and the best systems nearly reach the reference texts. In contrast, for translation with sample bitexts, the spread of the systems is bigger, and the best scores are lower, highlighting the need to concentrate on terminology extraction rather than its use from an explicit source. We also evaluate the grammaticality of the generated texts in Basque and Polish and observe slight trends toward using dictionary forms of the terms and assigning the most frequent grammemes.},
  url       = {https://aclanthology.org/2026.wmt-1.51}
}