<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="passban-etal-2016-enriching">
    <titleInfo>
        <title>Enriching Phrase Tables for Statistical Machine Translation Using Mixed Embeddings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Peyman</namePart>
        <namePart type="family">Passban</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qun</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andy</namePart>
        <namePart type="family">Way</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2016-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yuji</namePart>
            <namePart type="family">Matsumoto</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rashmi</namePart>
            <namePart type="family">Prasad</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>The COLING 2016 Organizing Committee</publisher>
            <place>
                <placeTerm type="text">Osaka, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The phrase table is considered to be the main bilingual resource for the phrase-based statistical machine translation (PBSMT) model. During translation, a source sentence is decomposed into several phrases. The best match of each source phrase is selected among several target-side counterparts within the phrase table, and processed by the decoder to generate a sentence-level translation. The best match is chosen according to several factors, including a set of bilingual features. PBSMT engines by default provide four probability scores in phrase tables which are considered as the main set of bilingual features. Our goal is to enrich that set of features, as a better feature set should yield better translations. We propose new scores generated by a Convolutional Neural Network (CNN) which indicate the semantic relatedness of phrase pairs. We evaluate our model in different experimental settings with different language pairs. We observe significant improvements when the proposed features are incorporated into the PBSMT pipeline.</abstract>
    <identifier type="citekey">passban-etal-2016-enriching</identifier>
    <location>
        <url>https://aclanthology.org/C16-1243</url>
    </location>
    <part>
        <date>2016-12</date>
        <extent unit="page">
            <start>2582</start>
            <end>2591</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Enriching Phrase Tables for Statistical Machine Translation Using Mixed Embeddings
%A Passban, Peyman
%A Liu, Qun
%A Way, Andy
%Y Matsumoto, Yuji
%Y Prasad, Rashmi
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F passban-etal-2016-enriching
%X The phrase table is considered to be the main bilingual resource for the phrase-based statistical machine translation (PBSMT) model. During translation, a source sentence is decomposed into several phrases. The best match of each source phrase is selected among several target-side counterparts within the phrase table, and processed by the decoder to generate a sentence-level translation. The best match is chosen according to several factors, including a set of bilingual features. PBSMT engines by default provide four probability scores in phrase tables which are considered as the main set of bilingual features. Our goal is to enrich that set of features, as a better feature set should yield better translations. We propose new scores generated by a Convolutional Neural Network (CNN) which indicate the semantic relatedness of phrase pairs. We evaluate our model in different experimental settings with different language pairs. We observe significant improvements when the proposed features are incorporated into the PBSMT pipeline.
%U https://aclanthology.org/C16-1243
%P 2582-2591

Markdown (Informal)

[Enriching Phrase Tables for Statistical Machine Translation Using Mixed Embeddings](https://aclanthology.org/C16-1243) (Passban et al., COLING 2016)

• Enriching Phrase Tables for Statistical Machine Translation Using Mixed Embeddings (Passban et al., COLING 2016)

ACL

• Peyman Passban, Qun Liu, and Andy Way. 2016. Enriching Phrase Tables for Statistical Machine Translation Using Mixed Embeddings. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2582–2591, Osaka, Japan. The COLING 2016 Organizing Committee.