<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nieminen-etal-2025-implementing">
    <titleInfo>
        <title>Implementing and Evaluating Multi-source Retrieval-Augmented Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tommi</namePart>
        <namePart type="family">Nieminen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jörg</namePart>
        <namePart type="family">Tiedemann</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sami</namePart>
        <namePart type="family">Virpioja</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>In recent years, neural machine translation (NMT) systems have been integrated with external databases with the aim of improving machine translation (MT) quality and enforcing domain-specific terminology and other conventions in the MT output. Most of the work in incorporating external knowledge with NMT has concentrated on integrating a single source of information, usually either a terminology database or a translation memory. However, in real-life translation scenarios, all relevant knowledge sources should be used in parallel. In this article, we evaluate different methods of integrating external knowledge from multiple sources in a single NMT system. In addition to training single models trained to utilize multiple kinds of information, we also ensemble models that have been trained to utilize a single type of information. We evaluate our models against state-of-the-art LLMs using an extensive purpose-built English to Finnish test suite.</abstract>
    <identifier type="citekey">nieminen-etal-2025-implementing</identifier>
    <identifier type="doi">10.18653/v1/2025.wmt-1.20</identifier>
    <location>
        <url>https://aclanthology.org/2025.wmt-1.20/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>327</start>
            <end>339</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Implementing and Evaluating Multi-source Retrieval-Augmented Translation
%A Nieminen, Tommi
%A Tiedemann, Jörg
%A Virpioja, Sami
%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 nieminen-etal-2025-implementing
%X In recent years, neural machine translation (NMT) systems have been integrated with external databases with the aim of improving machine translation (MT) quality and enforcing domain-specific terminology and other conventions in the MT output. Most of the work in incorporating external knowledge with NMT has concentrated on integrating a single source of information, usually either a terminology database or a translation memory. However, in real-life translation scenarios, all relevant knowledge sources should be used in parallel. In this article, we evaluate different methods of integrating external knowledge from multiple sources in a single NMT system. In addition to training single models trained to utilize multiple kinds of information, we also ensemble models that have been trained to utilize a single type of information. We evaluate our models against state-of-the-art LLMs using an extensive purpose-built English to Finnish test suite.
%R 10.18653/v1/2025.wmt-1.20
%U https://aclanthology.org/2025.wmt-1.20/
%U https://doi.org/10.18653/v1/2025.wmt-1.20
%P 327-339

Markdown (Informal)

[Implementing and Evaluating Multi-source Retrieval-Augmented Translation](https://aclanthology.org/2025.wmt-1.20/) (Nieminen et al., WMT 2025)

• Implementing and Evaluating Multi-source Retrieval-Augmented Translation (Nieminen et al., WMT 2025)

ACL

• Tommi Nieminen, Jörg Tiedemann, and Sami Virpioja. 2025. Implementing and Evaluating Multi-source Retrieval-Augmented Translation. In Proceedings of the Tenth Conference on Machine Translation, pages 327–339, Suzhou, China. Association for Computational Linguistics.