<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2024-efficient">
    <titleInfo>
        <title>Efficient Terminology Integration for LLM-based Translation in Specialized Domains</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sejoon</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mingi</namePart>
        <namePart type="family">Sung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jeonghwan</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hyunkuk</namePart>
        <namePart type="family">Lim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jorge</namePart>
        <namePart type="family">Gimenez Perez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Ninth 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">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Traditional machine translation methods typically involve training models directly on large parallel corpora, with limited emphasis on specialized terminology. However, In specialized fields such as patents, finance, biomedical domains, terminology is crucial for translation, with many terminologies that should not be translated based on semantics of the sentence but should be translated following agreed-upon conventions. In this paper we introduce a methodology that efficiently trains models with a smaller amount of data while preserving the accuracy of terminology translation. The terminology extraction model generates a glossary from existing training datasets and further refines the LLM by instructing it to effectively incorporate these terms into translations. We achieve this through a systematic process of term extraction and glossary creation using the Trie Tree algorithm, followed by data reconstruction to teach the LLM how to integrate these specialized terms. This methodology enhances the model’s ability to handle specialized terminology and ensures high-quality translations, particularly in fields where term consistency is crucial. Our approach has demonstrated exceptional performance, achieving the highest translation score among participants in the WMT patent task to date, showcasing its effectiveness and broad applicability in specialized translation domains where general methods often fall short.</abstract>
    <identifier type="citekey">kim-etal-2024-efficient</identifier>
    <location>
        <url>https://aclanthology.org/2024.wmt-1.51</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>636</start>
            <end>642</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Efficient Terminology Integration for LLM-based Translation in Specialized Domains
%A Kim, Sejoon
%A Sung, Mingi
%A Lee, Jeonghwan
%A Lim, Hyunkuk
%A Gimenez Perez, Jorge
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Ninth Conference on Machine Translation
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F kim-etal-2024-efficient
%X Traditional machine translation methods typically involve training models directly on large parallel corpora, with limited emphasis on specialized terminology. However, In specialized fields such as patents, finance, biomedical domains, terminology is crucial for translation, with many terminologies that should not be translated based on semantics of the sentence but should be translated following agreed-upon conventions. In this paper we introduce a methodology that efficiently trains models with a smaller amount of data while preserving the accuracy of terminology translation. The terminology extraction model generates a glossary from existing training datasets and further refines the LLM by instructing it to effectively incorporate these terms into translations. We achieve this through a systematic process of term extraction and glossary creation using the Trie Tree algorithm, followed by data reconstruction to teach the LLM how to integrate these specialized terms. This methodology enhances the model’s ability to handle specialized terminology and ensures high-quality translations, particularly in fields where term consistency is crucial. Our approach has demonstrated exceptional performance, achieving the highest translation score among participants in the WMT patent task to date, showcasing its effectiveness and broad applicability in specialized translation domains where general methods often fall short.
%U https://aclanthology.org/2024.wmt-1.51
%P 636-642

Markdown (Informal)

[Efficient Terminology Integration for LLM-based Translation in Specialized Domains](https://aclanthology.org/2024.wmt-1.51) (Kim et al., WMT 2024)

• Efficient Terminology Integration for LLM-based Translation in Specialized Domains (Kim et al., WMT 2024)

ACL

• Sejoon Kim, Mingi Sung, Jeonghwan Lee, Hyunkuk Lim, and Jorge Gimenez Perez. 2024. Efficient Terminology Integration for LLM-based Translation in Specialized Domains. In Proceedings of the Ninth Conference on Machine Translation, pages 636–642, Miami, Florida, USA. Association for Computational Linguistics.