<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marie-etal-2020-tagged">
    <titleInfo>
        <title>Tagged Back-translation Revisited: Why Does It Really Work?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Benjamin</namePart>
        <namePart type="family">Marie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Raphael</namePart>
        <namePart type="family">Rubino</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Atsushi</namePart>
        <namePart type="family">Fujita</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>In this paper, we show that neural machine translation (NMT) systems trained on large back-translated data overfit some of the characteristics of machine-translated texts. Such NMT systems better translate human-produced translations, i.e., translationese, but may largely worsen the translation quality of original texts. Our analysis reveals that adding a simple tag to back-translations prevents this quality degradation and improves on average the overall translation quality by helping the NMT system to distinguish back-translated data from original parallel data during training. We also show that, in contrast to high-resource configurations, NMT systems trained in low-resource settings are much less vulnerable to overfit back-translations. We conclude that the back-translations in the training data should always be tagged especially when the origin of the text to be translated is unknown.</abstract>
    <identifier type="citekey">marie-etal-2020-tagged</identifier>
    <identifier type="doi">10.18653/v1/2020.acl-main.532</identifier>
    <location>
        <url>https://aclanthology.org/2020.acl-main.532/</url>
    </location>
    <part>
        <date>2020-07</date>
        <extent unit="page">
            <start>5990</start>
            <end>5997</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Tagged Back-translation Revisited: Why Does It Really Work?
%A Marie, Benjamin
%A Rubino, Raphael
%A Fujita, Atsushi
%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 marie-etal-2020-tagged
%X In this paper, we show that neural machine translation (NMT) systems trained on large back-translated data overfit some of the characteristics of machine-translated texts. Such NMT systems better translate human-produced translations, i.e., translationese, but may largely worsen the translation quality of original texts. Our analysis reveals that adding a simple tag to back-translations prevents this quality degradation and improves on average the overall translation quality by helping the NMT system to distinguish back-translated data from original parallel data during training. We also show that, in contrast to high-resource configurations, NMT systems trained in low-resource settings are much less vulnerable to overfit back-translations. We conclude that the back-translations in the training data should always be tagged especially when the origin of the text to be translated is unknown.
%R 10.18653/v1/2020.acl-main.532
%U https://aclanthology.org/2020.acl-main.532/
%U https://doi.org/10.18653/v1/2020.acl-main.532
%P 5990-5997

Markdown (Informal)

[Tagged Back-translation Revisited: Why Does It Really Work?](https://aclanthology.org/2020.acl-main.532/) (Marie et al., ACL 2020)

• Tagged Back-translation Revisited: Why Does It Really Work? (Marie et al., ACL 2020)

ACL

• Benjamin Marie, Raphael Rubino, and Atsushi Fujita. 2020. Tagged Back-translation Revisited: Why Does It Really Work?. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5990–5997, Online. Association for Computational Linguistics.