<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vamvas-etal-2023-trained">
    <titleInfo>
        <title>Trained MT Metrics Learn to Cope with Machine-translated References</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jannis</namePart>
        <namePart type="family">Vamvas</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tobias</namePart>
        <namePart type="family">Domhan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sony</namePart>
        <namePart type="family">Trenous</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rico</namePart>
        <namePart type="family">Sennrich</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eva</namePart>
        <namePart type="family">Hasler</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Eighth Conference on Machine Translation</title>
        </titleInfo>
        <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">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">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">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Neural metrics trained on human evaluations of MT tend to correlate well with human judgments, but their behavior is not fully understood. In this paper, we perform a controlled experiment and compare a baseline metric that has not been trained on human evaluations (Prism) to a trained version of the same metric (Prism+FT). Surprisingly, we find that Prism+FT becomes more robust to machine-translated references, which are a notorious problem in MT evaluation. This suggests that the effects of metric training go beyond the intended effect of improving overall correlation with human judgments.</abstract>
    <identifier type="citekey">vamvas-etal-2023-trained</identifier>
    <identifier type="doi">10.18653/v1/2023.wmt-1.95</identifier>
    <location>
        <url>https://aclanthology.org/2023.wmt-1.95</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>983</start>
            <end>995</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Trained MT Metrics Learn to Cope with Machine-translated References
%A Vamvas, Jannis
%A Domhan, Tobias
%A Trenous, Sony
%A Sennrich, Rico
%A Hasler, Eva
%Y Koehn, Philipp
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Monz, Christof
%S Proceedings of the Eighth Conference on Machine Translation
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F vamvas-etal-2023-trained
%X Neural metrics trained on human evaluations of MT tend to correlate well with human judgments, but their behavior is not fully understood. In this paper, we perform a controlled experiment and compare a baseline metric that has not been trained on human evaluations (Prism) to a trained version of the same metric (Prism+FT). Surprisingly, we find that Prism+FT becomes more robust to machine-translated references, which are a notorious problem in MT evaluation. This suggests that the effects of metric training go beyond the intended effect of improving overall correlation with human judgments.
%R 10.18653/v1/2023.wmt-1.95
%U https://aclanthology.org/2023.wmt-1.95
%U https://doi.org/10.18653/v1/2023.wmt-1.95
%P 983-995

Markdown (Informal)

[Trained MT Metrics Learn to Cope with Machine-translated References](https://aclanthology.org/2023.wmt-1.95) (Vamvas et al., WMT 2023)

• Trained MT Metrics Learn to Cope with Machine-translated References (Vamvas et al., WMT 2023)

ACL

• Jannis Vamvas, Tobias Domhan, Sony Trenous, Rico Sennrich, and Eva Hasler. 2023. Trained MT Metrics Learn to Cope with Machine-translated References. In Proceedings of the Eighth Conference on Machine Translation, pages 983–995, Singapore. Association for Computational Linguistics.