<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pinnis-etal-2026-tildes">
    <titleInfo>
        <title>Tilde’s Submission for the WMT2026 Shared Task on Terminology Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Marcis</namePart>
        <namePart type="family">Pinnis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Martins</namePart>
        <namePart type="family">Kronis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Emils</namePart>
        <namePart type="family">Grims</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ervins</namePart>
        <namePart type="family">Jakovelis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Roberts</namePart>
        <namePart type="family">Rozis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Toms</namePart>
        <namePart type="family">Bergmanis</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>This paper describes Tilde’s submissions to the WMT 2026 Shared Task on Terminology. For both subtasks, we use TildeOpen-30B, which we instruction-tune for translation using terminology glossaries and translation memories, and we detail the construction of the training data augmented with these resources. For Task 1, we compare three term recognition methods aimed at reducing large term collections to subsets relevant for translation: fuzzy search, stemming with exact-match search, and stemming with fuzzy search. For Task 2, we compare extracting a glossary from the provided translation memory and integrating it in context against using retrieved translation-memory entries directly as few-shot examples. As the shared task provides neither reference translations nor a development set, we validate our design decisions with an LLM-as-a-judge protocol. In-domain term collections reduce translation errors by up to 22% relative to translating without terminology, whereas out-of-domain collections yield only marginal gains, and glossaries extracted from the translation memory outperform few-shot translation with retrieved entries.</abstract>
    <identifier type="citekey">pinnis-etal-2026-tildes</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.121/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1860</start>
            <end>1872</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Tilde’s Submission for the WMT2026 Shared Task on Terminology Translation
%A Pinnis, Marcis
%A Kronis, Martins
%A Grims, Emils
%A Jakovelis, Ervins
%A Rozis, Roberts
%A Bergmanis, Toms
%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 pinnis-etal-2026-tildes
%X This paper describes Tilde’s submissions to the WMT 2026 Shared Task on Terminology. For both subtasks, we use TildeOpen-30B, which we instruction-tune for translation using terminology glossaries and translation memories, and we detail the construction of the training data augmented with these resources. For Task 1, we compare three term recognition methods aimed at reducing large term collections to subsets relevant for translation: fuzzy search, stemming with exact-match search, and stemming with fuzzy search. For Task 2, we compare extracting a glossary from the provided translation memory and integrating it in context against using retrieved translation-memory entries directly as few-shot examples. As the shared task provides neither reference translations nor a development set, we validate our design decisions with an LLM-as-a-judge protocol. In-domain term collections reduce translation errors by up to 22% relative to translating without terminology, whereas out-of-domain collections yield only marginal gains, and glossaries extracted from the translation memory outperform few-shot translation with retrieved entries.
%U https://aclanthology.org/2026.wmt-main.121/
%P 1860-1872

Markdown (Informal)

[Tilde’s Submission for the WMT2026 Shared Task on Terminology Translation](https://aclanthology.org/2026.wmt-main.121/) (Pinnis et al., WMT 2026)

• Tilde’s Submission for the WMT2026 Shared Task on Terminology Translation (Pinnis et al., WMT 2026)

ACL

• Marcis Pinnis, Martins Kronis, Emils Grims, Ervins Jakovelis, Roberts Rozis, and Toms Bergmanis. 2026. Tilde’s Submission for the WMT2026 Shared Task on Terminology Translation. In Proceedings of the Eleventh Conference on Machine Translation, pages 1860–1872, Budapest, Hungary. Association for Computational Linguistics.