<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hayashi-etal-2009-structural">
    <titleInfo>
        <title>Structural support vector machines for log-linear approach in statistical machine translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Katsuhiko</namePart>
        <namePart type="family">Hayashi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Taro</namePart>
        <namePart type="family">Watanabe</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hajime</namePart>
        <namePart type="family">Tsukada</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hideki</namePart>
        <namePart type="family">Isozaki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2009-dec 1-2</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 6th International Workshop on Spoken Language Translation: Papers</title>
        </titleInfo>
        <originInfo>
            <place>
                <placeTerm type="text">Tokyo, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Minimum error rate training (MERT) is a widely used learning method for statistical machine translation. In this paper, we present a SVM-based training method to enhance generalization ability. We extend MERT optimization by maximizing the margin between the reference and incorrect translations under the L2-norm prior to avoid overfitting problem. Translation accuracy obtained by our proposed methods is more stable in various conditions than that obtained by MERT. Our experimental results on the French-English WMT08 shared task show that degrade of our proposed methods is smaller than that of MERT in case of small training data or out-of-domain test data.</abstract>
    <identifier type="citekey">hayashi-etal-2009-structural</identifier>
    <location>
        <url>https://aclanthology.org/2009.iwslt-papers.3/</url>
    </location>
    <part>
        <date>2009-dec 1-2</date>
        <extent unit="page">
            <start>144</start>
            <end>151</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Structural support vector machines for log-linear approach in statistical machine translation
%A Hayashi, Katsuhiko
%A Watanabe, Taro
%A Tsukada, Hajime
%A Isozaki, Hideki
%S Proceedings of the 6th International Workshop on Spoken Language Translation: Papers
%D 2009
%8 dec 1 2
%C Tokyo, Japan
%F hayashi-etal-2009-structural
%X Minimum error rate training (MERT) is a widely used learning method for statistical machine translation. In this paper, we present a SVM-based training method to enhance generalization ability. We extend MERT optimization by maximizing the margin between the reference and incorrect translations under the L2-norm prior to avoid overfitting problem. Translation accuracy obtained by our proposed methods is more stable in various conditions than that obtained by MERT. Our experimental results on the French-English WMT08 shared task show that degrade of our proposed methods is smaller than that of MERT in case of small training data or out-of-domain test data.
%U https://aclanthology.org/2009.iwslt-papers.3/
%P 144-151

Markdown (Informal)

[Structural support vector machines for log-linear approach in statistical machine translation](https://aclanthology.org/2009.iwslt-papers.3/) (Hayashi et al., IWSLT 2009)

• Structural support vector machines for log-linear approach in statistical machine translation (Hayashi et al., IWSLT 2009)

ACL

• Katsuhiko Hayashi, Taro Watanabe, Hajime Tsukada, and Hideki Isozaki. 2009. Structural support vector machines for log-linear approach in statistical machine translation. In Proceedings of the 6th International Workshop on Spoken Language Translation: Papers, pages 144–151, Tokyo, Japan.