<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liao-etal-2021-back">
    <titleInfo>
        <title>Back-translation for Large-Scale Multilingual Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Baohao</namePart>
        <namePart type="family">Liao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shahram</namePart>
        <namePart type="family">Khadivi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sanjika</namePart>
        <namePart type="family">Hewavitharana</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Sixth Conference on Machine Translation</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper illustrates our approach to the shared task on large-scale multilingual machine translation in the sixth conference on machine translation (WMT-21). In this work, we aim to build a single multilingual translation system with a hypothesis that a universal cross-language representation leads to better multilingual translation performance. We extend the exploration of different back-translation methods from bilingual translation to multilingual translation. Better performance is obtained by the constrained sampling method, which is different from the finding of the bilingual translation. Besides, we also explore the effect of vocabularies and the amount of synthetic data. Surprisingly, the smaller size of vocabularies perform better, and the extensive monolingual English data offers a modest improvement. We submitted to both the small tasks and achieve the second place.</abstract>
    <identifier type="citekey">liao-etal-2021-back</identifier>
    <location>
        <url>https://aclanthology.org/2021.wmt-1.50</url>
    </location>
    <part>
        <date>2021-nov</date>
        <extent unit="page">
            <start>418</start>
            <end>424</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Back-translation for Large-Scale Multilingual Machine Translation
%A Liao, Baohao
%A Khadivi, Shahram
%A Hewavitharana, Sanjika
%S Proceedings of the Sixth Conference on Machine Translation
%D 2021
%8 nov
%I Association for Computational Linguistics
%C Online
%F liao-etal-2021-back
%X This paper illustrates our approach to the shared task on large-scale multilingual machine translation in the sixth conference on machine translation (WMT-21). In this work, we aim to build a single multilingual translation system with a hypothesis that a universal cross-language representation leads to better multilingual translation performance. We extend the exploration of different back-translation methods from bilingual translation to multilingual translation. Better performance is obtained by the constrained sampling method, which is different from the finding of the bilingual translation. Besides, we also explore the effect of vocabularies and the amount of synthetic data. Surprisingly, the smaller size of vocabularies perform better, and the extensive monolingual English data offers a modest improvement. We submitted to both the small tasks and achieve the second place.
%U https://aclanthology.org/2021.wmt-1.50
%P 418-424

Markdown (Informal)

[Back-translation for Large-Scale Multilingual Machine Translation](https://aclanthology.org/2021.wmt-1.50) (Liao et al., WMT 2021)

• Back-translation for Large-Scale Multilingual Machine Translation (Liao et al., WMT 2021)

ACL

• Baohao Liao, Shahram Khadivi, and Sanjika Hewavitharana. 2021. Back-translation for Large-Scale Multilingual Machine Translation. In Proceedings of the Sixth Conference on Machine Translation, pages 418–424, Online. Association for Computational Linguistics.