Antecedent Selection for Sluicing: Structure and Content

Pranav Anand, Daniel Hardt

    Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningpeer review

    139 Downloads (Pure)

    Abstract

    Sluicing is an elliptical process where the majority of a question can go unpronounced as long as there is a salient antecedent in previous discourse. This paper considers the task of antecedent selection: finding the correct antecedent for a given case of sluicing. We argue that both syntactic and discourse relationships are important in antecedent selection, and we construct linguistically sophisticated features that describe the relevant relationships. We also define features that describe the relation of the content of the antecedent and the sluice type. We develop a linear model which achieves accuracy of 72.4%, a substantial improvement over a strong manually constructed baseline. Feature analysis confirms that both syntactic and discourse features are important in antecedent selection.
    OriginalsprogEngelsk
    TitelProceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
    RedaktørerJian Su, Kevin Duh, Xavier Carreras
    Antal sider10
    UdgivelsesstedAustin
    ForlagAssociation for Computational Linguistics
    Publikationsdato2016
    Sider1234-1243
    KapitelD16-1131
    ISBN (Elektronisk)9781945626258
    DOI
    StatusUdgivet - 2016
    Begivenhed2016 Conference on Empirical Methods in Natural Language Processing - Hilton Austin & Westin Hotel , Austin, USA
    Varighed: 1 nov. 20165 nov. 2016
    http://www.emnlp2016.net

    Konference

    Konference2016 Conference on Empirical Methods in Natural Language Processing
    LokationHilton Austin & Westin Hotel
    Land/OmrådeUSA
    ByAustin
    Periode01/11/201605/11/2016
    Internetadresse

    Citationsformater