<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2022-focus">
    <titleInfo>
        <title>Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Liang</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Runxin</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Baobao</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Smaranda</namePart>
            <namePart type="family">Muresan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Preslav</namePart>
            <namePart type="family">Nakov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aline</namePart>
            <namePart type="family">Villavicencio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dublin, Ireland</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models. However, we argue that simply applying both techniques can be conflicting and even leads to sub-optimal performance. When allocating smoothed probability, original label smoothing treats the source-side words that would never appear in the target language equally to the real target-side words, which could bias the translation model. To address this issue, we propose Masked Label Smoothing (MLS), a new mechanism that masks the soft label probability of source-side words to zero. Simple yet effective, MLS manages to better integrate label smoothing with vocabulary sharing. Our extensive experiments show that MLS consistently yields improvement over original label smoothing on different datasets, including bilingual and multilingual translation from both translation quality and model’s calibration. Our code is released at https://github.com/PKUnlp-icler/MLS</abstract>
    <identifier type="citekey">chen-etal-2022-focus</identifier>
    <identifier type="doi">10.18653/v1/2022.acl-short.74</identifier>
    <location>
        <url>https://aclanthology.org/2022.acl-short.74</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>665</start>
            <end>671</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation
%A Chen, Liang
%A Xu, Runxin
%A Chang, Baobao
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F chen-etal-2022-focus
%X Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models. However, we argue that simply applying both techniques can be conflicting and even leads to sub-optimal performance. When allocating smoothed probability, original label smoothing treats the source-side words that would never appear in the target language equally to the real target-side words, which could bias the translation model. To address this issue, we propose Masked Label Smoothing (MLS), a new mechanism that masks the soft label probability of source-side words to zero. Simple yet effective, MLS manages to better integrate label smoothing with vocabulary sharing. Our extensive experiments show that MLS consistently yields improvement over original label smoothing on different datasets, including bilingual and multilingual translation from both translation quality and model’s calibration. Our code is released at https://github.com/PKUnlp-icler/MLS
%R 10.18653/v1/2022.acl-short.74
%U https://aclanthology.org/2022.acl-short.74
%U https://doi.org/10.18653/v1/2022.acl-short.74
%P 665-671

Markdown (Informal)

[Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation](https://aclanthology.org/2022.acl-short.74) (Chen et al., ACL 2022)

• Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation (Chen et al., ACL 2022)

ACL

• Liang Chen, Runxin Xu, and Baobao Chang. 2022. Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 665–671, Dublin, Ireland. Association for Computational Linguistics.