<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cao-xiong-2018-encoding">
    <titleInfo>
        <title>Encoding Gated Translation Memory into Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Qian</namePart>
        <namePart type="family">Cao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Deyi</namePart>
        <namePart type="family">Xiong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-oct-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ellen</namePart>
            <namePart type="family">Riloff</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Chiang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Julia</namePart>
            <namePart type="family">Hockenmaier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun’ichi</namePart>
            <namePart type="family">Tsujii</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Translation memories (TM) facilitate human translators to reuse existing repetitive translation fragments. In this paper, we propose a novel method to combine the strengths of both TM and neural machine translation (NMT) for high-quality translation. We treat the target translation of a TM match as an additional reference input and encode it into NMT with an extra encoder. A gating mechanism is further used to balance the impact of the TM match on the NMT decoder. Experiment results on the UN corpus demonstrate that when fuzzy matches are higher than 50%, the quality of NMT translation can be significantly improved by over 10 BLEU points.</abstract>
    <identifier type="citekey">cao-xiong-2018-encoding</identifier>
    <identifier type="doi">10.18653/v1/D18-1340</identifier>
    <location>
        <url>https://aclanthology.org/D18-1340</url>
    </location>
    <part>
        <date>2018-oct-nov</date>
        <extent unit="page">
            <start>3042</start>
            <end>3047</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Encoding Gated Translation Memory into Neural Machine Translation
%A Cao, Qian
%A Xiong, Deyi
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F cao-xiong-2018-encoding
%X Translation memories (TM) facilitate human translators to reuse existing repetitive translation fragments. In this paper, we propose a novel method to combine the strengths of both TM and neural machine translation (NMT) for high-quality translation. We treat the target translation of a TM match as an additional reference input and encode it into NMT with an extra encoder. A gating mechanism is further used to balance the impact of the TM match on the NMT decoder. Experiment results on the UN corpus demonstrate that when fuzzy matches are higher than 50%, the quality of NMT translation can be significantly improved by over 10 BLEU points.
%R 10.18653/v1/D18-1340
%U https://aclanthology.org/D18-1340
%U https://doi.org/10.18653/v1/D18-1340
%P 3042-3047

Markdown (Informal)

[Encoding Gated Translation Memory into Neural Machine Translation](https://aclanthology.org/D18-1340) (Cao & Xiong, EMNLP 2018)

• Encoding Gated Translation Memory into Neural Machine Translation (Cao & Xiong, EMNLP 2018)

ACL

• Qian Cao and Deyi Xiong. 2018. Encoding Gated Translation Memory into Neural Machine Translation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3042–3047, Brussels, Belgium. Association for Computational Linguistics.