@InProceedings{sukhareva-enikeeva:2026:wmt,
  author    = {Sukhareva, Maria  and  Enikeeva, Ekaterina},
  title     = {Retrieval-Augmented Terminology Translation for English-Russian: A Multi-Domain Study},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {718--733},
  abstract  = {Neural machine translation reaches near-human quality on general-domain text but systematically fails on specialized terminology, where polysemous and low-frequency terms carry domain-specific meanings absent from general training data. We investigate two complementary interventions for English-Russian specialized translation across ten professional domains: (i) a four-stage retrieval-augmented pipeline of LLM-based term extraction, domain classification, lemma-based knowledge-base retrieval, and glossary-augmented translation; and (ii) a preference-based fine-tuning stage combining supervised fine-tuning (SFT) with Contrastive Preference Optimization (CPO) layered on top of retrieval. We release an open multi-domain English-Russian terminology knowledge base of 50,000 terms with 120,161 domain-tagged translations, a 200-item curated test set selected for terminology difficulty, and a 1,300-item Wikipedia-derived test set. Across four open base models, retrieval-augmented prompting alone delivers the bulk of the terminology gain and already exceeds the two commercial reference systems; the additional preference-tuning stage contributes only a small further gain at a measurable fluency cost. The pattern transfers to the WMT25 Terminology Translation Task, the most recent iteration of the shared task that included English-Russian as a language pair.},
  url       = {https://aclanthology.org/2026.wmt-1.40}
}