<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kohn-baumann-2016-predictive">
    <titleInfo>
        <title>Predictive Incremental Parsing Helps Language Modeling</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Arne</namePart>
        <namePart type="family">Köhn</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Timo</namePart>
        <namePart type="family">Baumann</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>Predictive incremental parsing produces syntactic representations of sentences as they are produced, e.g. by typing or speaking. In order to generate connected parses for such unfinished sentences, upcoming word types can be hypothesized and structurally integrated with already realized words. For example, the presence of a determiner as the last word of a sentence prefix may indicate that a noun will appear somewhere in the completion of that sentence, and the determiner can be attached to the predicted noun. We combine the forward-looking parser predictions with backward-looking N-gram histories and analyze in a set of experiments the impact on language models, i.e. stronger discriminative power but also higher data sparsity. Conditioning N-gram models, MaxEnt models or RNN-LMs on parser predictions yields perplexity reductions of about 6%. Our method (a) retains online decoding capabilities and (b) incurs relatively little computational overhead which sets it apart from previous approaches that use syntax for language modeling. Our method is particularly attractive for modular systems that make use of a syntax parser anyway, e.g. as part of an understanding pipeline where predictive parsing improves language modeling at no additional cost.</abstract>
    <identifier type="citekey">kohn-baumann-2016-predictive</identifier>
    <location>
        <url>https://aclanthology.org/C16-1026</url>
    </location>
    <part>
        <date>2016-12</date>
        <extent unit="page">
            <start>268</start>
            <end>277</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Predictive Incremental Parsing Helps Language Modeling
%A Köhn, Arne
%A Baumann, Timo
%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 kohn-baumann-2016-predictive
%X Predictive incremental parsing produces syntactic representations of sentences as they are produced, e.g. by typing or speaking. In order to generate connected parses for such unfinished sentences, upcoming word types can be hypothesized and structurally integrated with already realized words. For example, the presence of a determiner as the last word of a sentence prefix may indicate that a noun will appear somewhere in the completion of that sentence, and the determiner can be attached to the predicted noun. We combine the forward-looking parser predictions with backward-looking N-gram histories and analyze in a set of experiments the impact on language models, i.e. stronger discriminative power but also higher data sparsity. Conditioning N-gram models, MaxEnt models or RNN-LMs on parser predictions yields perplexity reductions of about 6%. Our method (a) retains online decoding capabilities and (b) incurs relatively little computational overhead which sets it apart from previous approaches that use syntax for language modeling. Our method is particularly attractive for modular systems that make use of a syntax parser anyway, e.g. as part of an understanding pipeline where predictive parsing improves language modeling at no additional cost.
%U https://aclanthology.org/C16-1026
%P 268-277

Markdown (Informal)

[Predictive Incremental Parsing Helps Language Modeling](https://aclanthology.org/C16-1026) (Köhn & Baumann, COLING 2016)

• Predictive Incremental Parsing Helps Language Modeling (Köhn & Baumann, COLING 2016)

ACL

• Arne Köhn and Timo Baumann. 2016. Predictive Incremental Parsing Helps Language Modeling. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 268–277, Osaka, Japan. The COLING 2016 Organizing Committee.