<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gu-etal-2019-improved">
    <titleInfo>
        <title>Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jiatao</namePart>
        <namePart type="family">Gu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yong</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kyunghyun</namePart>
        <namePart type="family">Cho</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Victor</namePart>
        <namePart type="given">O.K.</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Traum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Màrquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Zero-shot translation, translating between language pairs on which a Neural Machine Translation (NMT) system has never been trained, is an emergent property when training the system in multilingual settings. However, naive training for zero-shot NMT easily fails, and is sensitive to hyper-parameter setting. The performance typically lags far behind the more conventional pivot-based approach which translates twice using a third language as a pivot. In this work, we address the degeneracy problem due to capturing spurious correlations by quantitatively analyzing the mutual information between language IDs of the source and decoded sentences. Inspired by this analysis, we propose to use two simple but effective approaches: (1) decoder pre-training; (2) back-translation. These methods show significant improvement (4 22 BLEU points) over the vanilla zero-shot translation on three challenging multilingual datasets, and achieve similar or better results than the pivot-based approach.</abstract>
    <identifier type="citekey">gu-etal-2019-improved</identifier>
    <identifier type="doi">10.18653/v1/P19-1121</identifier>
    <location>
        <url>https://aclanthology.org/P19-1121</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>1258</start>
            <end>1268</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations
%A Gu, Jiatao
%A Wang, Yong
%A Cho, Kyunghyun
%A Li, Victor O.K.
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F gu-etal-2019-improved
%X Zero-shot translation, translating between language pairs on which a Neural Machine Translation (NMT) system has never been trained, is an emergent property when training the system in multilingual settings. However, naive training for zero-shot NMT easily fails, and is sensitive to hyper-parameter setting. The performance typically lags far behind the more conventional pivot-based approach which translates twice using a third language as a pivot. In this work, we address the degeneracy problem due to capturing spurious correlations by quantitatively analyzing the mutual information between language IDs of the source and decoded sentences. Inspired by this analysis, we propose to use two simple but effective approaches: (1) decoder pre-training; (2) back-translation. These methods show significant improvement (4 22 BLEU points) over the vanilla zero-shot translation on three challenging multilingual datasets, and achieve similar or better results than the pivot-based approach.
%R 10.18653/v1/P19-1121
%U https://aclanthology.org/P19-1121
%U https://doi.org/10.18653/v1/P19-1121
%P 1258-1268

Markdown (Informal)

[Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations](https://aclanthology.org/P19-1121) (Gu et al., ACL 2019)

• Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations (Gu et al., ACL 2019)

ACL

• Jiatao Gu, Yong Wang, Kyunghyun Cho, and Victor O.K. Li. 2019. Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1258–1268, Florence, Italy. Association for Computational Linguistics.