<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cagan-etal-2017-data">
    <titleInfo>
        <title>Data-Driven Broad-Coverage Grammars for Opinionated Natural Language Generation (ONLG)</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tomer</namePart>
        <namePart type="family">Cagan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Stefan</namePart>
        <namePart type="given">L</namePart>
        <namePart type="family">Frank</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Reut</namePart>
        <namePart type="family">Tsarfaty</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Regina</namePart>
            <namePart type="family">Barzilay</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Min-Yen</namePart>
            <namePart type="family">Kan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vancouver, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Opinionated Natural Language Generation (ONLG) is a new, challenging, task that aims to automatically generate human-like, subjective, responses to opinionated articles online. We present a data-driven architecture for ONLG that generates subjective responses triggered by users’ agendas, consisting of topics and sentiments, and based on wide-coverage automatically-acquired generative grammars. We compare three types of grammatical representations that we design for ONLG, which interleave different layers of linguistic information and are induced from a new, enriched dataset we developed. Our evaluation shows that generation with Relational-Realizational (Tsarfaty and Sima’an, 2008) inspired grammar gets better language model scores than lexicalized grammars ‘a la Collins (2003), and that the latter gets better human-evaluation scores. We also show that conditioning the generation on topic models makes generated responses more relevant to the document content.</abstract>
    <identifier type="citekey">cagan-etal-2017-data</identifier>
    <identifier type="doi">10.18653/v1/P17-1122</identifier>
    <location>
        <url>https://aclanthology.org/P17-1122</url>
    </location>
    <part>
        <date>2017-07</date>
        <extent unit="page">
            <start>1331</start>
            <end>1341</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Data-Driven Broad-Coverage Grammars for Opinionated Natural Language Generation (ONLG)
%A Cagan, Tomer
%A Frank, Stefan L.
%A Tsarfaty, Reut
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F cagan-etal-2017-data
%X Opinionated Natural Language Generation (ONLG) is a new, challenging, task that aims to automatically generate human-like, subjective, responses to opinionated articles online. We present a data-driven architecture for ONLG that generates subjective responses triggered by users’ agendas, consisting of topics and sentiments, and based on wide-coverage automatically-acquired generative grammars. We compare three types of grammatical representations that we design for ONLG, which interleave different layers of linguistic information and are induced from a new, enriched dataset we developed. Our evaluation shows that generation with Relational-Realizational (Tsarfaty and Sima’an, 2008) inspired grammar gets better language model scores than lexicalized grammars ‘a la Collins (2003), and that the latter gets better human-evaluation scores. We also show that conditioning the generation on topic models makes generated responses more relevant to the document content.
%R 10.18653/v1/P17-1122
%U https://aclanthology.org/P17-1122
%U https://doi.org/10.18653/v1/P17-1122
%P 1331-1341

Markdown (Informal)

[Data-Driven Broad-Coverage Grammars for Opinionated Natural Language Generation (ONLG)](https://aclanthology.org/P17-1122) (Cagan et al., ACL 2017)

• Data-Driven Broad-Coverage Grammars for Opinionated Natural Language Generation (ONLG) (Cagan et al., ACL 2017)

ACL

• Tomer Cagan, Stefan L. Frank, and Reut Tsarfaty. 2017. Data-Driven Broad-Coverage Grammars for Opinionated Natural Language Generation (ONLG). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1331–1341, Vancouver, Canada. Association for Computational Linguistics.