<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pong-2025-contextual">
    <titleInfo>
        <title>Contextual Selection of Pseudo-terminology Constraints for Terminology-aware Neural Machine Translation in the IT Domain</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Benjamin</namePart>
        <namePart type="family">Pong</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 system paper describes the development of a Neural Machine Translation system that is adapted to the Information Technology (IT) domain, and is able to translate specialized IT-related terminologies. Despite the popularity of incorporating terminology constraints at training time to develop terminology-aware Neural Machine Translation engines, one of the main issues is: In the absence of terminology references for training, and with the proliferation of source-target alignments, how does one select word alignments as pseudo-terminology constraints? The system in this work uses the encoder’s final hidden states as proxies for terminologies, and selects word alignments with the highest norm as pseudo-terminology constraints for inline annotation at run-time. It compares this context-based approach against a conventional statistical approach, where terminology-constraints are selected based on a low-frequency threshold. The systems were evaluated for general translation quality and Terminology Success Rates, with results that validate the effectiveness of the contextual approach.</abstract>
    <identifier type="citekey">pong-2025-contextual</identifier>
    <location>
        <url>https://aclanthology.org/2025.wmt-1.109/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>1292</start>
            <end>1301</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Contextual Selection of Pseudo-terminology Constraints for Terminology-aware Neural Machine Translation in the IT Domain
%A Pong, Benjamin
%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 pong-2025-contextual
%X This system paper describes the development of a Neural Machine Translation system that is adapted to the Information Technology (IT) domain, and is able to translate specialized IT-related terminologies. Despite the popularity of incorporating terminology constraints at training time to develop terminology-aware Neural Machine Translation engines, one of the main issues is: In the absence of terminology references for training, and with the proliferation of source-target alignments, how does one select word alignments as pseudo-terminology constraints? The system in this work uses the encoder’s final hidden states as proxies for terminologies, and selects word alignments with the highest norm as pseudo-terminology constraints for inline annotation at run-time. It compares this context-based approach against a conventional statistical approach, where terminology-constraints are selected based on a low-frequency threshold. The systems were evaluated for general translation quality and Terminology Success Rates, with results that validate the effectiveness of the contextual approach.
%U https://aclanthology.org/2025.wmt-1.109/
%P 1292-1301

Markdown (Informal)

[Contextual Selection of Pseudo-terminology Constraints for Terminology-aware Neural Machine Translation in the IT Domain](https://aclanthology.org/2025.wmt-1.109/) (Pong, WMT 2025)

• Contextual Selection of Pseudo-terminology Constraints for Terminology-aware Neural Machine Translation in the IT Domain (Pong, WMT 2025)

ACL

• Benjamin Pong. 2025. Contextual Selection of Pseudo-terminology Constraints for Terminology-aware Neural Machine Translation in the IT Domain. In Proceedings of the Tenth Conference on Machine Translation, pages 1292–1301, Suzhou, China. Association for Computational Linguistics.