Papers for

localization quality assurance teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

TermJudge improves machine translation terminology evaluation with context

TermJudge: A Document-Level Metric Judging, Not Counting, Terminology in Machine Translation Evaluation

Abstract: Existing automatic metrics for evaluating terminological use in machine translation (MT) penalise any divergence from a fixed reference, conflating translation errors with the valid terminological variation that human translators routinely produce. We introduce TermJudge, a document-level terminology metric that assigns an interpretable verdict to every term occurrence: glossary-conforming occurrences are settled deterministically, while divergences are assessed under a two-step LLM-as-judge procedure using the full document context: the first detects and labels terminology errors; the second sorts valid document-level variations from inconsistencies. Validated against expert error annotations and document-level human MQM scores, TermJudge ranks first in both system- and segment-level meta-evaluation, ahead of glossary-conformity and quality-estimation baselines. When applied to eight systems translating academic documents, under two prompting conditions, we observe that glossary injection improves terminology translation in all paired comparisons, by removing genuine errors rather than valid variation. TermJudge is released as open-source code.

Mon 28 SeptArtificial Intelligence
The gist
Machine translations sometimes use different valid terms than a fixed glossary, causing traditional evaluation tools to wrongly count those as mistakes. This paper presents TermJudge, a new way to check translated terms by deciding whether each usage matches the glossary or is a valid variation or an error, using the whole document for context. The authors show TermJudge outperforms other methods in matching expert judgments. They also find that adding glossary terms helps improve the quality of terminology in translations.
Open → 2609.35017v1