<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pham-etal-2021-revisiting">
    <titleInfo>
        <title>Revisiting Multi-Domain Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">MinhQuang</namePart>
        <namePart type="family">Pham</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Josep</namePart>
        <namePart type="given">Maria</namePart>
        <namePart type="family">Crego</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">François</namePart>
        <namePart type="family">Yvon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>When building machine translation systems, one often needs to make the best out of heterogeneous sets of parallel data in training, and to robustly handle inputs from unexpected domains in testing. This multi-domain scenario has attracted a lot of recent work that fall under the general umbrella of transfer learning. In this study, we revisit multi-domain machine translation, with the aim to formulate the motivations for developing such systems and the associated expectations with respect to performance. Our experiments with a large sample of multi-domain systems show that most of these expectations are hardly met and suggest that further work is needed to better analyze the current behaviour of multi-domain systems and to make them fully hold their promises.</abstract>
    <identifier type="citekey">pham-etal-2021-revisiting</identifier>
    <identifier type="doi">10.1162/tacl_a_00351</identifier>
    <location>
        <url>https://aclanthology.org/2021.tacl-1.2/</url>
    </location>
    <part>
        <date>2021</date>
        <detail type="volume"><number>9</number></detail>
        <extent unit="page">
            <start>17</start>
            <end>35</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Revisiting Multi-Domain Machine Translation
%A Pham, MinhQuang
%A Crego, Josep Maria
%A Yvon, François
%J Transactions of the Association for Computational Linguistics
%D 2021
%V 9
%I MIT Press
%C Cambridge, MA
%F pham-etal-2021-revisiting
%X When building machine translation systems, one often needs to make the best out of heterogeneous sets of parallel data in training, and to robustly handle inputs from unexpected domains in testing. This multi-domain scenario has attracted a lot of recent work that fall under the general umbrella of transfer learning. In this study, we revisit multi-domain machine translation, with the aim to formulate the motivations for developing such systems and the associated expectations with respect to performance. Our experiments with a large sample of multi-domain systems show that most of these expectations are hardly met and suggest that further work is needed to better analyze the current behaviour of multi-domain systems and to make them fully hold their promises.
%R 10.1162/tacl_a_00351
%U https://aclanthology.org/2021.tacl-1.2/
%U https://doi.org/10.1162/tacl_a_00351
%P 17-35

Markdown (Informal)

[Revisiting Multi-Domain Machine Translation](https://aclanthology.org/2021.tacl-1.2/) (Pham et al., TACL 2021)

• Revisiting Multi-Domain Machine Translation (Pham et al., TACL 2021)

ACL

• MinhQuang Pham, Josep Maria Crego, and François Yvon. 2021. Revisiting Multi-Domain Machine Translation. Transactions of the Association for Computational Linguistics, 9:17–35.