<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2023-integrating">
    <titleInfo>
        <title>Integrating Translation Memories into Non-Autoregressive Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jitao</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Josep</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>2023-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</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>Non-autoregressive machine translation (NAT) has recently made great progress. However, most works to date have focused on standard translation tasks, even though some edit-based NAT models, such as the Levenshtein Transformer (LevT), seem well suited to translate with a Translation Memory (TM). This is the scenario considered here. We first analyze the vanilla LevT model and explain why it does not do well in this setting. We then propose a new variant, TM-LevT, and show how to effectively train this model. By modifying the data presentation and introducing an extra deletion operation, we obtain performance that are on par with an autoregressive approach, while reducing the decoding load. We also show that incorporating TMs during training dispenses to use knowledge distillation, a well-known trick used to mitigate the multimodality issue.</abstract>
    <identifier type="citekey">xu-etal-2023-integrating</identifier>
    <identifier type="doi">10.18653/v1/2023.eacl-main.96</identifier>
    <location>
        <url>https://aclanthology.org/2023.eacl-main.96/</url>
    </location>
    <part>
        <date>2023-05</date>
        <extent unit="page">
            <start>1326</start>
            <end>1338</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Integrating Translation Memories into Non-Autoregressive Machine Translation
%A Xu, Jitao
%A Crego, Josep
%A Yvon, François
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F xu-etal-2023-integrating
%X Non-autoregressive machine translation (NAT) has recently made great progress. However, most works to date have focused on standard translation tasks, even though some edit-based NAT models, such as the Levenshtein Transformer (LevT), seem well suited to translate with a Translation Memory (TM). This is the scenario considered here. We first analyze the vanilla LevT model and explain why it does not do well in this setting. We then propose a new variant, TM-LevT, and show how to effectively train this model. By modifying the data presentation and introducing an extra deletion operation, we obtain performance that are on par with an autoregressive approach, while reducing the decoding load. We also show that incorporating TMs during training dispenses to use knowledge distillation, a well-known trick used to mitigate the multimodality issue.
%R 10.18653/v1/2023.eacl-main.96
%U https://aclanthology.org/2023.eacl-main.96/
%U https://doi.org/10.18653/v1/2023.eacl-main.96
%P 1326-1338

Markdown (Informal)

[Integrating Translation Memories into Non-Autoregressive Machine Translation](https://aclanthology.org/2023.eacl-main.96/) (Xu et al., EACL 2023)

• Integrating Translation Memories into Non-Autoregressive Machine Translation (Xu et al., EACL 2023)

ACL

• Jitao Xu, Josep Crego, and François Yvon. 2023. Integrating Translation Memories into Non-Autoregressive Machine Translation. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1326–1338, Dubrovnik, Croatia. Association for Computational Linguistics.