<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sennrich-2015-modelling">
    <titleInfo>
        <title>Modelling and Optimizing on Syntactic N-Grams for Statistical Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rico</namePart>
        <namePart type="family">Sennrich</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2015</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>The role of language models in SMT is to promote fluent translation output, but traditional n-gram language models are unable to capture fluency phenomena between distant words, such as some morphological agreement phenomena, subcategorisation, and syntactic collocations with string-level gaps. Syntactic language models have the potential to fill this modelling gap. We propose a language model for dependency structures that is relational rather than configurational and thus particularly suited for languages with a (relatively) free word order. It is trainable with Neural Networks, and not only improves over standard n-gram language models, but also outperforms related syntactic language models. We empirically demonstrate its effectiveness in terms of perplexity and as a feature function in string-to-tree SMT from English to German and Russian. We also show that using a syntactic evaluation metric to tune the log-linear parameters of an SMT system further increases translation quality when coupled with a syntactic language model.</abstract>
    <identifier type="citekey">sennrich-2015-modelling</identifier>
    <identifier type="doi">10.1162/tacl_a_00131</identifier>
    <location>
        <url>https://aclanthology.org/Q15-1013</url>
    </location>
    <part>
        <date>2015</date>
        <detail type="volume"><number>3</number></detail>
        <extent unit="page">
            <start>169</start>
            <end>182</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Modelling and Optimizing on Syntactic N-Grams for Statistical Machine Translation
%A Sennrich, Rico
%J Transactions of the Association for Computational Linguistics
%D 2015
%V 3
%I MIT Press
%C Cambridge, MA
%F sennrich-2015-modelling
%X The role of language models in SMT is to promote fluent translation output, but traditional n-gram language models are unable to capture fluency phenomena between distant words, such as some morphological agreement phenomena, subcategorisation, and syntactic collocations with string-level gaps. Syntactic language models have the potential to fill this modelling gap. We propose a language model for dependency structures that is relational rather than configurational and thus particularly suited for languages with a (relatively) free word order. It is trainable with Neural Networks, and not only improves over standard n-gram language models, but also outperforms related syntactic language models. We empirically demonstrate its effectiveness in terms of perplexity and as a feature function in string-to-tree SMT from English to German and Russian. We also show that using a syntactic evaluation metric to tune the log-linear parameters of an SMT system further increases translation quality when coupled with a syntactic language model.
%R 10.1162/tacl_a_00131
%U https://aclanthology.org/Q15-1013
%U https://doi.org/10.1162/tacl_a_00131
%P 169-182

Markdown (Informal)

[Modelling and Optimizing on Syntactic N-Grams for Statistical Machine Translation](https://aclanthology.org/Q15-1013) (Sennrich, TACL 2015)

• Modelling and Optimizing on Syntactic N-Grams for Statistical Machine Translation (Sennrich, TACL 2015)

ACL

• Rico Sennrich. 2015. Modelling and Optimizing on Syntactic N-Grams for Statistical Machine Translation. Transactions of the Association for Computational Linguistics, 3:169–182.