<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tamura-etal-2023-masked">
    <titleInfo>
        <title>Does Masked Language Model Pre-training with Artificial Data Improve Low-resource Neural Machine Translation?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hiroto</namePart>
        <namePart type="family">Tamura</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tosho</namePart>
        <namePart type="family">Hirasawa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hwichan</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mamoru</namePart>
        <namePart type="family">Komachi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Andreas</namePart>
            <namePart type="family">Vlachos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Isabelle</namePart>
            <namePart type="family">Augenstein</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dubrovnik, Croatia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Pre-training masked language models (MLMs) with artificial data has been proven beneficial for several natural language processing tasks such as natural language understanding and summarization; however, it has been less explored for neural machine translation (NMT).A previous study revealed the benefit of transfer learning for NMT in a limited setup, which differs from MLM.In this study, we prepared two kinds of artificial data and compared the translation performance of NMT when pre-trained with MLM.In addition to the random sequences, we created artificial data mimicking token frequency information from the real world. Our results showed that pre-training the models with artificial data by MLM improves translation performance in low-resource situations. Additionally, we found that pre-training on artificial data created considering token frequency information facilitates improved performance.</abstract>
    <identifier type="citekey">tamura-etal-2023-masked</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-eacl.166</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-eacl.166</url>
    </location>
    <part>
        <date>2023-05</date>
        <extent unit="page">
            <start>2216</start>
            <end>2225</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Does Masked Language Model Pre-training with Artificial Data Improve Low-resource Neural Machine Translation?
%A Tamura, Hiroto
%A Hirasawa, Tosho
%A Kim, Hwichan
%A Komachi, Mamoru
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F tamura-etal-2023-masked
%X Pre-training masked language models (MLMs) with artificial data has been proven beneficial for several natural language processing tasks such as natural language understanding and summarization; however, it has been less explored for neural machine translation (NMT).A previous study revealed the benefit of transfer learning for NMT in a limited setup, which differs from MLM.In this study, we prepared two kinds of artificial data and compared the translation performance of NMT when pre-trained with MLM.In addition to the random sequences, we created artificial data mimicking token frequency information from the real world. Our results showed that pre-training the models with artificial data by MLM improves translation performance in low-resource situations. Additionally, we found that pre-training on artificial data created considering token frequency information facilitates improved performance.
%R 10.18653/v1/2023.findings-eacl.166
%U https://aclanthology.org/2023.findings-eacl.166
%U https://doi.org/10.18653/v1/2023.findings-eacl.166
%P 2216-2225

Markdown (Informal)

[Does Masked Language Model Pre-training with Artificial Data Improve Low-resource Neural Machine Translation?](https://aclanthology.org/2023.findings-eacl.166) (Tamura et al., Findings 2023)

• Does Masked Language Model Pre-training with Artificial Data Improve Low-resource Neural Machine Translation? (Tamura et al., Findings 2023)

ACL

• Hiroto Tamura, Tosho Hirasawa, Hwichan Kim, and Mamoru Komachi. 2023. Does Masked Language Model Pre-training with Artificial Data Improve Low-resource Neural Machine Translation?. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2216–2225, Dubrovnik, Croatia. Association for Computational Linguistics.