<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shin-lee-2018-multi">
    <titleInfo>
        <title>Multi-encoder Transformer Network for Automatic Post-Editing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jaehun</namePart>
        <namePart type="family">Shin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jong-Hyeok</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-oct</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Third Conference on Machine Translation: Shared Task Papers</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Belgium, Brussels</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper describes the POSTECH’s submission to the WMT 2018 shared task on Automatic Post-Editing (APE). We propose a new neural end-to-end post-editing model based on the transformer network. We modified the encoder-decoder attention to reflect the relation between the machine translation output, the source and the post-edited translation in APE problem. Experiments on WMT17 English-German APE data set show an improvement in both TER and BLEU score over the best result of WMT17 APE shared task. Our primary submission achieves -4.52 TER and +6.81 BLEU score on PBSMT task and -0.13 TER and +0.40 BLEU score for NMT task compare to the baseline.</abstract>
    <identifier type="citekey">shin-lee-2018-multi</identifier>
    <identifier type="doi">10.18653/v1/W18-6470</identifier>
    <location>
        <url>https://aclanthology.org/W18-6470</url>
    </location>
    <part>
        <date>2018-oct</date>
        <extent unit="page">
            <start>840</start>
            <end>845</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multi-encoder Transformer Network for Automatic Post-Editing
%A Shin, Jaehun
%A Lee, Jong-Hyeok
%S Proceedings of the Third Conference on Machine Translation: Shared Task Papers
%D 2018
%8 oct
%I Association for Computational Linguistics
%C Belgium, Brussels
%F shin-lee-2018-multi
%X This paper describes the POSTECH’s submission to the WMT 2018 shared task on Automatic Post-Editing (APE). We propose a new neural end-to-end post-editing model based on the transformer network. We modified the encoder-decoder attention to reflect the relation between the machine translation output, the source and the post-edited translation in APE problem. Experiments on WMT17 English-German APE data set show an improvement in both TER and BLEU score over the best result of WMT17 APE shared task. Our primary submission achieves -4.52 TER and +6.81 BLEU score on PBSMT task and -0.13 TER and +0.40 BLEU score for NMT task compare to the baseline.
%R 10.18653/v1/W18-6470
%U https://aclanthology.org/W18-6470
%U https://doi.org/10.18653/v1/W18-6470
%P 840-845

Markdown (Informal)

[Multi-encoder Transformer Network for Automatic Post-Editing](https://aclanthology.org/W18-6470) (Shin & Lee, 2018)

• Multi-encoder Transformer Network for Automatic Post-Editing (Shin & Lee, 2018)

ACL

• Jaehun Shin and Jong-Hyeok Lee. 2018. Multi-encoder Transformer Network for Automatic Post-Editing. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 840–845, Belgium, Brussels. Association for Computational Linguistics.