@inproceedings{sukhareva-enikeeva-2026-retrieval,
title = "Retrieval-Augmented Terminology Translation for {E}nglish-{R}ussian: A Multi-Domain Study",
author = "Sukhareva, Maria and
Enikeeva, Ekaterina",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Eleventh Conference on Machine Translation",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wmt-main.40/",
pages = "711--726",
ISBN = "979-8-89176-474-3",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sukhareva-enikeeva-2026-retrieval">
<titleInfo>
<title>Retrieval-Augmented Terminology Translation for English-Russian: A Multi-Domain Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Sukhareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Enikeeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eleventh Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-474-3</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">sukhareva-enikeeva-2026-retrieval</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.40/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>711</start>
<end>726</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Retrieval-Augmented Terminology Translation for English-Russian: A Multi-Domain Study
%A Sukhareva, Maria
%A Enikeeva, Ekaterina
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F sukhareva-enikeeva-2026-retrieval
%X 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.
%U https://aclanthology.org/2026.wmt-main.40/
%P 711-726
Markdown (Informal)
[Retrieval-Augmented Terminology Translation for English-Russian: A Multi-Domain Study](https://aclanthology.org/2026.wmt-main.40/) (Sukhareva & Enikeeva, WMT 2026)
ACL