Antecedent Selection for Sluicing: Structure and Content

Pranav Anand, Daniel Hardt

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    141 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.
    Original languageEnglish
    Title of host publicationProceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
    EditorsJian Su, Kevin Duh, Xavier Carreras
    Number of pages10
    Place of PublicationAustin
    PublisherAssociation for Computational Linguistics
    Publication date2016
    Pages1234-1243
    ChapterD16-1131
    ISBN (Electronic)9781945626258
    DOIs
    Publication statusPublished - 2016
    Event2016 Conference on Empirical Methods in Natural Language Processing - Hilton Austin & Westin Hotel , Austin, United States
    Duration: 1 Nov 20165 Nov 2016
    http://www.emnlp2016.net

    Conference

    Conference2016 Conference on Empirical Methods in Natural Language Processing
    LocationHilton Austin & Westin Hotel
    Country/TerritoryUnited States
    CityAustin
    Period01/11/201605/11/2016
    Internet address

    Cite this