<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2020-balancing">
    <titleInfo>
        <title>Balancing Training for Multilingual Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xinyi</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yulia</namePart>
        <namePart type="family">Tsvetkov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Graham</namePart>
        <namePart type="family">Neubig</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Dan</namePart>
            <namePart type="family">Jurafsky</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Chai</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Natalie</namePart>
            <namePart type="family">Schluter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joel</namePart>
            <namePart type="family">Tetreault</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>When training multilingual machine translation (MT) models that can translate to/from multiple languages, we are faced with imbalanced training sets: some languages have much more training data than others. Standard practice is to up-sample less resourced languages to increase representation, and the degree of up-sampling has a large effect on the overall performance. In this paper, we propose a method that instead automatically learns how to weight training data through a data scorer that is optimized to maximize performance on all test languages. Experiments on two sets of languages under both one-to-many and many-to-one MT settings show our method not only consistently outperforms heuristic baselines in terms of average performance, but also offers flexible control over the performance of which languages are optimized.</abstract>
    <identifier type="citekey">wang-etal-2020-balancing</identifier>
    <identifier type="doi">10.18653/v1/2020.acl-main.754</identifier>
    <location>
        <url>https://aclanthology.org/2020.acl-main.754/</url>
    </location>
    <part>
        <date>2020-07</date>
        <extent unit="page">
            <start>8526</start>
            <end>8537</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Balancing Training for Multilingual Neural Machine Translation
%A Wang, Xinyi
%A Tsvetkov, Yulia
%A Neubig, Graham
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F wang-etal-2020-balancing
%X When training multilingual machine translation (MT) models that can translate to/from multiple languages, we are faced with imbalanced training sets: some languages have much more training data than others. Standard practice is to up-sample less resourced languages to increase representation, and the degree of up-sampling has a large effect on the overall performance. In this paper, we propose a method that instead automatically learns how to weight training data through a data scorer that is optimized to maximize performance on all test languages. Experiments on two sets of languages under both one-to-many and many-to-one MT settings show our method not only consistently outperforms heuristic baselines in terms of average performance, but also offers flexible control over the performance of which languages are optimized.
%R 10.18653/v1/2020.acl-main.754
%U https://aclanthology.org/2020.acl-main.754/
%U https://doi.org/10.18653/v1/2020.acl-main.754
%P 8526-8537

Markdown (Informal)

[Balancing Training for Multilingual Neural Machine Translation](https://aclanthology.org/2020.acl-main.754/) (Wang et al., ACL 2020)

• Balancing Training for Multilingual Neural Machine Translation (Wang et al., ACL 2020)

ACL

• Xinyi Wang, Yulia Tsvetkov, and Graham Neubig. 2020. Balancing Training for Multilingual Neural Machine Translation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8526–8537, Online. Association for Computational Linguistics.