<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qu-watanabe-2022-adapting">
    <titleInfo>
        <title>Adapting to Non-Centered Languages for Zero-shot Multilingual Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhi</namePart>
        <namePart type="family">Qu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Taro</namePart>
        <namePart type="family">Watanabe</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 29th International Conference on Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <publisher>International Committee on Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Multilingual neural machine translation can translate unseen language pairs during training, i.e. zero-shot translation. However, the zero-shot translation is always unstable. Although prior works attributed the instability to the domination of central language, e.g. English, we supplement this viewpoint with the strict dependence of non-centered languages. In this work, we propose a simple, lightweight yet effective language-specific modeling method by adapting to non-centered languages and combining the shared information and the language-specific information to counteract the instability of zero-shot translation. Experiments with Transformer on IWSLT17, Europarl, TED talks, and OPUS-100 datasets show that our method not only performs better than strong baselines in centered data conditions but also can easily fit non-centered data conditions. By further investigating the layer attribution, we show that our proposed method can disentangle the coupled representation in the correct direction.</abstract>
    <identifier type="citekey">qu-watanabe-2022-adapting</identifier>
    <location>
        <url>https://aclanthology.org/2022.coling-1.467</url>
    </location>
    <part>
        <date>2022-10</date>
        <extent unit="page">
            <start>5251</start>
            <end>5265</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Adapting to Non-Centered Languages for Zero-shot Multilingual Translation
%A Qu, Zhi
%A Watanabe, Taro
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F qu-watanabe-2022-adapting
%X Multilingual neural machine translation can translate unseen language pairs during training, i.e. zero-shot translation. However, the zero-shot translation is always unstable. Although prior works attributed the instability to the domination of central language, e.g. English, we supplement this viewpoint with the strict dependence of non-centered languages. In this work, we propose a simple, lightweight yet effective language-specific modeling method by adapting to non-centered languages and combining the shared information and the language-specific information to counteract the instability of zero-shot translation. Experiments with Transformer on IWSLT17, Europarl, TED talks, and OPUS-100 datasets show that our method not only performs better than strong baselines in centered data conditions but also can easily fit non-centered data conditions. By further investigating the layer attribution, we show that our proposed method can disentangle the coupled representation in the correct direction.
%U https://aclanthology.org/2022.coling-1.467
%P 5251-5265

Markdown (Informal)

[Adapting to Non-Centered Languages for Zero-shot Multilingual Translation](https://aclanthology.org/2022.coling-1.467) (Qu & Watanabe, COLING 2022)

• Adapting to Non-Centered Languages for Zero-shot Multilingual Translation (Qu & Watanabe, COLING 2022)

ACL

• Zhi Qu and Taro Watanabe. 2022. Adapting to Non-Centered Languages for Zero-shot Multilingual Translation. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5251–5265, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.