<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="duan-zhao-2023-encoder">
    <titleInfo>
        <title>Encoder and Decoder, Not One Less for Pre-trained Language Model Sponsored NMT</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sufeng</namePart>
        <namePart type="family">Duan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hai</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Well pre-trained contextualized representations from pre-trained language model (PLM) have been shown helpful for enhancing various natural language processing tasks, surely including neural machine translation (NMT). However, existing methods either consider encoder-only enhancement or rely on specific multilingual PLMs, which leads to a much larger model or give up potentially helpful knowledge from target PLMs. In this paper, we propose a new monolingual PLM-sponsored NMT model to let both encoder and decoder enjoy PLM enhancement to alleviate such obvious inconvenience. Especially, incorporating a newly proposed frequency-weighted embedding transformation algorithm, PLM embeddings can be effectively exploited in terms of the representations of the NMT decoder. We evaluate our model on IWSLT14 En-De, De-En, WMT14 En-De, and En-Fr tasks, and the results show that our proposed PLM enhancement gives significant improvement and even helps achieve new state-of-the-art.</abstract>
    <identifier type="citekey">duan-zhao-2023-encoder</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.222</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.222</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>3602</start>
            <end>3613</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Encoder and Decoder, Not One Less for Pre-trained Language Model Sponsored NMT
%A Duan, Sufeng
%A Zhao, Hai
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F duan-zhao-2023-encoder
%X Well pre-trained contextualized representations from pre-trained language model (PLM) have been shown helpful for enhancing various natural language processing tasks, surely including neural machine translation (NMT). However, existing methods either consider encoder-only enhancement or rely on specific multilingual PLMs, which leads to a much larger model or give up potentially helpful knowledge from target PLMs. In this paper, we propose a new monolingual PLM-sponsored NMT model to let both encoder and decoder enjoy PLM enhancement to alleviate such obvious inconvenience. Especially, incorporating a newly proposed frequency-weighted embedding transformation algorithm, PLM embeddings can be effectively exploited in terms of the representations of the NMT decoder. We evaluate our model on IWSLT14 En-De, De-En, WMT14 En-De, and En-Fr tasks, and the results show that our proposed PLM enhancement gives significant improvement and even helps achieve new state-of-the-art.
%R 10.18653/v1/2023.findings-acl.222
%U https://aclanthology.org/2023.findings-acl.222
%U https://doi.org/10.18653/v1/2023.findings-acl.222
%P 3602-3613

Markdown (Informal)

[Encoder and Decoder, Not One Less for Pre-trained Language Model Sponsored NMT](https://aclanthology.org/2023.findings-acl.222) (Duan & Zhao, Findings 2023)

• Encoder and Decoder, Not One Less for Pre-trained Language Model Sponsored NMT (Duan & Zhao, Findings 2023)

ACL

• Sufeng Duan and Hai Zhao. 2023. Encoder and Decoder, Not One Less for Pre-trained Language Model Sponsored NMT. In Findings of the Association for Computational Linguistics: ACL 2023, pages 3602–3613, Toronto, Canada. Association for Computational Linguistics.