<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-komachi-2018-neural">
    <titleInfo>
        <title>Neural Machine Translation of Logographic Language Using Sub-character Level Information</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Longtu</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mamoru</namePart>
        <namePart type="family">Komachi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Third Conference on Machine Translation: Research Papers</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recent neural machine translation (NMT) systems have been greatly improved by encoder-decoder models with attention mechanisms and sub-word units. However, important differences between languages with logographic and alphabetic writing systems have long been overlooked. This study focuses on these differences and uses a simple approach to improve the performance of NMT systems utilizing decomposed sub-character level information for logographic languages. Our results indicate that our approach not only improves the translation capabilities of NMT systems between Chinese and English, but also further improves NMT systems between Chinese and Japanese, because it utilizes the shared information brought by similar sub-character units.</abstract>
    <identifier type="citekey">zhang-komachi-2018-neural</identifier>
    <identifier type="doi">10.18653/v1/W18-6303</identifier>
    <location>
        <url>https://aclanthology.org/W18-6303</url>
    </location>
    <part>
        <date>2018-10</date>
        <extent unit="page">
            <start>17</start>
            <end>25</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Neural Machine Translation of Logographic Language Using Sub-character Level Information
%A Zhang, Longtu
%A Komachi, Mamoru
%S Proceedings of the Third Conference on Machine Translation: Research Papers
%D 2018
%8 October
%I Association for Computational Linguistics
%C Brussels, Belgium
%F zhang-komachi-2018-neural
%X Recent neural machine translation (NMT) systems have been greatly improved by encoder-decoder models with attention mechanisms and sub-word units. However, important differences between languages with logographic and alphabetic writing systems have long been overlooked. This study focuses on these differences and uses a simple approach to improve the performance of NMT systems utilizing decomposed sub-character level information for logographic languages. Our results indicate that our approach not only improves the translation capabilities of NMT systems between Chinese and English, but also further improves NMT systems between Chinese and Japanese, because it utilizes the shared information brought by similar sub-character units.
%R 10.18653/v1/W18-6303
%U https://aclanthology.org/W18-6303
%U https://doi.org/10.18653/v1/W18-6303
%P 17-25

Markdown (Informal)

[Neural Machine Translation of Logographic Language Using Sub-character Level Information](https://aclanthology.org/W18-6303) (Zhang & Komachi, WMT 2018)

• Neural Machine Translation of Logographic Language Using Sub-character Level Information (Zhang & Komachi, WMT 2018)

ACL

• Longtu Zhang and Mamoru Komachi. 2018. Neural Machine Translation of Logographic Language Using Sub-character Level Information. In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 17–25, Brussels, Belgium. Association for Computational Linguistics.