@inproceedings{marchetti-etal-2026-star,
title = "{ST}a{R}-{MT}: Select, Translate, and Revise Pipeline for Terminology Aware Machine Translation",
author = "Marchetti, Guilherme and
Rocha, Gil and
Lopes Cardoso, Henrique and
Sousa-Silva, Rui",
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.118/",
pages = "1830--1839",
ISBN = "979-8-89176-474-3",
abstract = "To assess the progress in terminology-aware machine translation, the Terminology Shared Task is hosted alongside the Conference on Machine Translation (WMT). In this paper, we describe our submission to the shared task: STaR-MT. This is a three-step pipeline composed of (S)election, (T)ranslation, (a)nd (R)evision, focused on terminology-aware machine translation (MT). Our methodology adopts a lightweight agent-based design that selects relevant entries or examples and presents them to the translation agent, which uses a general-purpose LLM with a large context window to produce the initial output. Next, the revision agent uses language-specific models to improve translation quality for selected target languages. Experiments on the FLORES+ dataset with different model sizes in the pipeline suggest that machine translation pipelines can benefit from combining large general-purpose translation models with smaller, language-specific revision models, at least in some language pairs. While simple in architecture, this approach allows us to generate translations at the document level, with no need for pre-processing or paragraph splitting, and with minimal errors across most languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marchetti-etal-2026-star">
<titleInfo>
<title>STaR-MT: Select, Translate, and Revise Pipeline for Terminology Aware Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guilherme</namePart>
<namePart type="family">Marchetti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gil</namePart>
<namePart type="family">Rocha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henrique</namePart>
<namePart type="family">Lopes Cardoso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Sousa-Silva</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>To assess the progress in terminology-aware machine translation, the Terminology Shared Task is hosted alongside the Conference on Machine Translation (WMT). In this paper, we describe our submission to the shared task: STaR-MT. This is a three-step pipeline composed of (S)election, (T)ranslation, (a)nd (R)evision, focused on terminology-aware machine translation (MT). Our methodology adopts a lightweight agent-based design that selects relevant entries or examples and presents them to the translation agent, which uses a general-purpose LLM with a large context window to produce the initial output. Next, the revision agent uses language-specific models to improve translation quality for selected target languages. Experiments on the FLORES+ dataset with different model sizes in the pipeline suggest that machine translation pipelines can benefit from combining large general-purpose translation models with smaller, language-specific revision models, at least in some language pairs. While simple in architecture, this approach allows us to generate translations at the document level, with no need for pre-processing or paragraph splitting, and with minimal errors across most languages.</abstract>
<identifier type="citekey">marchetti-etal-2026-star</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.118/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1830</start>
<end>1839</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T STaR-MT: Select, Translate, and Revise Pipeline for Terminology Aware Machine Translation
%A Marchetti, Guilherme
%A Rocha, Gil
%A Lopes Cardoso, Henrique
%A Sousa-Silva, Rui
%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 marchetti-etal-2026-star
%X To assess the progress in terminology-aware machine translation, the Terminology Shared Task is hosted alongside the Conference on Machine Translation (WMT). In this paper, we describe our submission to the shared task: STaR-MT. This is a three-step pipeline composed of (S)election, (T)ranslation, (a)nd (R)evision, focused on terminology-aware machine translation (MT). Our methodology adopts a lightweight agent-based design that selects relevant entries or examples and presents them to the translation agent, which uses a general-purpose LLM with a large context window to produce the initial output. Next, the revision agent uses language-specific models to improve translation quality for selected target languages. Experiments on the FLORES+ dataset with different model sizes in the pipeline suggest that machine translation pipelines can benefit from combining large general-purpose translation models with smaller, language-specific revision models, at least in some language pairs. While simple in architecture, this approach allows us to generate translations at the document level, with no need for pre-processing or paragraph splitting, and with minimal errors across most languages.
%U https://aclanthology.org/2026.wmt-main.118/
%P 1830-1839
Markdown (Informal)
[STaR-MT: Select, Translate, and Revise Pipeline for Terminology Aware Machine Translation](https://aclanthology.org/2026.wmt-main.118/) (Marchetti et al., WMT 2026)
ACL