<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jaswal-2025-takes">
    <titleInfo>
        <title>It Takes Two: A Dual Stage Approach for Terminology-Aware Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Akshat</namePart>
        <namePart type="family">Jaswal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Tenth 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">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-341-8</identifier>
    </relatedItem>
    <abstract>This paper introduces DuTerm, a novel two-stage architecture for terminology-constrained machine translation. Our system combines a terminology-aware NMT model, adapted via fine-tuning on large-scale synthetic data, with a prompt-based LLM for post-editing. The LLM stage refines NMT output and enforces terminology adherence. We evaluate DuTerm on English-to German, English-to-Spanish, and English-to-Russian for the WMT 2025 Terminology Shared Task. We demonstrate that flexible, context-driven terminology handling by the LLM consistently yields higher quality translations than strict constraint enforcement. Our results highlight a critical trade-off, revealing that an LLM’s intrinsic knowledge often provides a stronger basis for high-quality translation than rigid, externally imposed constraints.</abstract>
    <identifier type="citekey">jaswal-2025-takes</identifier>
    <location>
        <url>https://aclanthology.org/2025.wmt-1.112/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>1344</start>
            <end>1350</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T It Takes Two: A Dual Stage Approach for Terminology-Aware Translation
%A Jaswal, Akshat
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Tenth Conference on Machine Translation
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-341-8
%F jaswal-2025-takes
%X This paper introduces DuTerm, a novel two-stage architecture for terminology-constrained machine translation. Our system combines a terminology-aware NMT model, adapted via fine-tuning on large-scale synthetic data, with a prompt-based LLM for post-editing. The LLM stage refines NMT output and enforces terminology adherence. We evaluate DuTerm on English-to German, English-to-Spanish, and English-to-Russian for the WMT 2025 Terminology Shared Task. We demonstrate that flexible, context-driven terminology handling by the LLM consistently yields higher quality translations than strict constraint enforcement. Our results highlight a critical trade-off, revealing that an LLM’s intrinsic knowledge often provides a stronger basis for high-quality translation than rigid, externally imposed constraints.
%U https://aclanthology.org/2025.wmt-1.112/
%P 1344-1350

Markdown (Informal)

[It Takes Two: A Dual Stage Approach for Terminology-Aware Translation](https://aclanthology.org/2025.wmt-1.112/) (Jaswal, WMT 2025)

• It Takes Two: A Dual Stage Approach for Terminology-Aware Translation (Jaswal, WMT 2025)

ACL

• Akshat Jaswal. 2025. It Takes Two: A Dual Stage Approach for Terminology-Aware Translation. In Proceedings of the Tenth Conference on Machine Translation, pages 1344–1350, Suzhou, China. Association for Computational Linguistics.