@inproceedings{dahan-etal-2026-improving,
title = "Improving Term Evaluation in Machine Translation: Variation Matters",
author = "Dahan, Nicolas and
Peng, Ziqian and
Yvon, Fran{\c{c}}ois and
Bawden, Rachel",
editor = "Briakou, Eleftheria and
Gwinnup, Jeremy and
Goel, Shivali",
booktitle = "Proceedings of the 17th Conference of the Association for Machine Translation in the {A}mericas (Volume 1: Research Track)",
month = aug,
year = "2026",
address = "Qu{\'e}bec City, Canada",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2026.amta-research.7/",
pages = "101--134",
abstract = "Terminology evaluation in machine translation (MT) usually assumes a single correct target form per source term, yet human translators routinely introduce variation that current metrics penalize as inconsistency. We examine how to account for this variation in document-level MT evaluation in English{--}French scientific translation, combining glossary-based accuracy, translation consistency, and a new cross-term variation (CTV) diagnostic measure that captures whether variation relationships are preserved across languages. On two parallel corpora translated by four MT systems, we find that (1) MT systems generate less target-side variation than human translators; (2) transfer patterns strongly depend on the variation type; (3) consistency rankings vary with the choice of metric; and (4) constraining MT with a glossary improves accuracy and consistency but degrades CTV by suppressing valid variation. We argue for variation-aware evaluation that conditions consistency penalties on whether target-side variation mirrors source-side variation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dahan-etal-2026-improving">
<titleInfo>
<title>Improving Term Evaluation in Machine Translation: Variation Matters</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Dahan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziqian</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Yvon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Bawden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eleftheria</namePart>
<namePart type="family">Briakou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Gwinnup</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shivali</namePart>
<namePart type="family">Goel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Québec City, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Terminology evaluation in machine translation (MT) usually assumes a single correct target form per source term, yet human translators routinely introduce variation that current metrics penalize as inconsistency. We examine how to account for this variation in document-level MT evaluation in English–French scientific translation, combining glossary-based accuracy, translation consistency, and a new cross-term variation (CTV) diagnostic measure that captures whether variation relationships are preserved across languages. On two parallel corpora translated by four MT systems, we find that (1) MT systems generate less target-side variation than human translators; (2) transfer patterns strongly depend on the variation type; (3) consistency rankings vary with the choice of metric; and (4) constraining MT with a glossary improves accuracy and consistency but degrades CTV by suppressing valid variation. We argue for variation-aware evaluation that conditions consistency penalties on whether target-side variation mirrors source-side variation.</abstract>
<identifier type="citekey">dahan-etal-2026-improving</identifier>
<location>
<url>https://aclanthology.org/2026.amta-research.7/</url>
</location>
<part>
<date>2026-08</date>
<extent unit="page">
<start>101</start>
<end>134</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Term Evaluation in Machine Translation: Variation Matters
%A Dahan, Nicolas
%A Peng, Ziqian
%A Yvon, François
%A Bawden, Rachel
%Y Briakou, Eleftheria
%Y Gwinnup, Jeremy
%Y Goel, Shivali
%S Proceedings of the 17th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)
%D 2026
%8 August
%I Association for Machine Translation in the Americas
%C Québec City, Canada
%F dahan-etal-2026-improving
%X Terminology evaluation in machine translation (MT) usually assumes a single correct target form per source term, yet human translators routinely introduce variation that current metrics penalize as inconsistency. We examine how to account for this variation in document-level MT evaluation in English–French scientific translation, combining glossary-based accuracy, translation consistency, and a new cross-term variation (CTV) diagnostic measure that captures whether variation relationships are preserved across languages. On two parallel corpora translated by four MT systems, we find that (1) MT systems generate less target-side variation than human translators; (2) transfer patterns strongly depend on the variation type; (3) consistency rankings vary with the choice of metric; and (4) constraining MT with a glossary improves accuracy and consistency but degrades CTV by suppressing valid variation. We argue for variation-aware evaluation that conditions consistency penalties on whether target-side variation mirrors source-side variation.
%U https://aclanthology.org/2026.amta-research.7/
%P 101-134
Markdown (Informal)
[Improving Term Evaluation in Machine Translation: Variation Matters](https://aclanthology.org/2026.amta-research.7/) (Dahan et al., AMTA 2026)
ACL
- Nicolas Dahan, Ziqian Peng, François Yvon, and Rachel Bawden. 2026. Improving Term Evaluation in Machine Translation: Variation Matters. In Proceedings of the 17th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track), pages 101–134, Québec City, Canada. Association for Machine Translation in the Americas.