<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ehara-2017-smt">
    <titleInfo>
        <title>SMT reranked NMT</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Terumasa</namePart>
        <namePart type="family">Ehara</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 4th Workshop on Asian Translation (WAT2017)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Toshiaki</namePart>
            <namePart type="family">Nakazawa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Isao</namePart>
            <namePart type="family">Goto</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Asian Federation of Natural Language Processing</publisher>
            <place>
                <placeTerm type="text">Taipei, Taiwan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>System architecture, experimental settings and experimental results of the EHR team for the WAT2017 tasks are described. We participate in three tasks: JPCen-ja, JPCzh-ja and JPCko-ja. Although the basic architecture of our system is NMT, reranking technique is conducted using SMT results. One of the major drawback of NMT is under-translation and over-translation. On the other hand, SMT infrequently makes such translations. So, using reranking of n-best NMT outputs by the SMT output, discarding such translations can be expected. We can improve BLEU score from 46.03 to 47.08 by this technique in JPCzh-ja task.</abstract>
    <identifier type="citekey">ehara-2017-smt</identifier>
    <location>
        <url>https://aclanthology.org/W17-5710</url>
    </location>
    <part>
        <date>2017-11</date>
        <extent unit="page">
            <start>119</start>
            <end>126</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SMT reranked NMT
%A Ehara, Terumasa
%Y Nakazawa, Toshiaki
%Y Goto, Isao
%S Proceedings of the 4th Workshop on Asian Translation (WAT2017)
%D 2017
%8 November
%I Asian Federation of Natural Language Processing
%C Taipei, Taiwan
%F ehara-2017-smt
%X System architecture, experimental settings and experimental results of the EHR team for the WAT2017 tasks are described. We participate in three tasks: JPCen-ja, JPCzh-ja and JPCko-ja. Although the basic architecture of our system is NMT, reranking technique is conducted using SMT results. One of the major drawback of NMT is under-translation and over-translation. On the other hand, SMT infrequently makes such translations. So, using reranking of n-best NMT outputs by the SMT output, discarding such translations can be expected. We can improve BLEU score from 46.03 to 47.08 by this technique in JPCzh-ja task.
%U https://aclanthology.org/W17-5710
%P 119-126

Markdown (Informal)

[SMT reranked NMT](https://aclanthology.org/W17-5710) (Ehara, WAT 2017)

• SMT reranked NMT (Ehara, WAT 2017)

ACL

• Terumasa Ehara. 2017. SMT reranked NMT. In Proceedings of the 4th Workshop on Asian Translation (WAT2017), pages 119–126, Taipei, Taiwan. Asian Federation of Natural Language Processing.