<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="libovicky-etal-2022-dont">
    <titleInfo>
        <title>Why don‘t people use character-level machine translation?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jindřich</namePart>
        <namePart type="family">Libovický</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Helmut</namePart>
        <namePart type="family">Schmid</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexander</namePart>
        <namePart type="family">Fraser</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>Findings of the Association for Computational Linguistics: ACL 2022</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>We present a literature and empirical survey that critically assesses the state of the art in character-level modeling for machine translation (MT). Despite evidence in the literature that character-level systems are comparable with subword systems, they are virtually never used in competitive setups in WMT competitions. We empirically show that even with recent modeling innovations in character-level natural language processing, character-level MT systems still struggle to match their subword-based counterparts. Character-level MT systems show neither better domain robustness, nor better morphological generalization, despite being often so motivated. However, we are able to show robustness towards source side noise and that translation quality does not degrade with increasing beam size at decoding time.</abstract>
    <identifier type="citekey">libovicky-etal-2022-dont</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-acl.194</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-acl.194/</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>2470</start>
            <end>2485</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Why don‘t people use character-level machine translation?
%A Libovický, Jindřich
%A Schmid, Helmut
%A Fraser, Alexander
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F libovicky-etal-2022-dont
%X We present a literature and empirical survey that critically assesses the state of the art in character-level modeling for machine translation (MT). Despite evidence in the literature that character-level systems are comparable with subword systems, they are virtually never used in competitive setups in WMT competitions. We empirically show that even with recent modeling innovations in character-level natural language processing, character-level MT systems still struggle to match their subword-based counterparts. Character-level MT systems show neither better domain robustness, nor better morphological generalization, despite being often so motivated. However, we are able to show robustness towards source side noise and that translation quality does not degrade with increasing beam size at decoding time.
%R 10.18653/v1/2022.findings-acl.194
%U https://aclanthology.org/2022.findings-acl.194/
%U https://doi.org/10.18653/v1/2022.findings-acl.194
%P 2470-2485

Markdown (Informal)

[Why don’t people use character-level machine translation?](https://aclanthology.org/2022.findings-acl.194/) (Libovický et al., Findings 2022)

• Why don’t people use character-level machine translation? (Libovický et al., Findings 2022)

ACL

• Jindřich Libovický, Helmut Schmid, and Alexander Fraser. 2022. Why don’t people use character-level machine translation?. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2470–2485, Dublin, Ireland. Association for Computational Linguistics.