Antecedent Selection for Sluicing: Structure and Content

Pranav Anand, Daniel Hardt

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

    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.
    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.
    LanguageEnglish
    Title of host publicationProceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
    EditorsJian Su, Kevin Duh, Xavier Carreras
    Place of PublicationAustin
    PublisherAssociation for Computational Linguistics
    Date2016
    Pages1234-1243
    ChapterD16-1131
    ISBN (Electronic)9781945626258
    StatePublished - 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
    CountryUnited States
    CityAustin
    Period01/11/201605/11/2016
    Internet address

    Cite this

    Anand, P., & Hardt, D. (2016). Antecedent Selection for Sluicing: Structure and Content. In J. Su, K. Duh, & X. Carreras (Eds.), Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (pp. 1234-1243). Austin: Association for Computational Linguistics.
    Anand, Pranav ; Hardt, Daniel. / Antecedent Selection for Sluicing : Structure and Content. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. editor / Jian Su ; Kevin Duh ; Xavier Carreras. Austin : Association for Computational Linguistics, 2016. pp. 1234-1243
    @inproceedings{f78b9dd2c04d43eeb6ee77b318ce27ca,
    title = "Antecedent Selection for Sluicing: Structure and Content",
    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.",
    author = "Pranav Anand and Daniel Hardt",
    year = "2016",
    language = "English",
    pages = "1234--1243",
    editor = "Jian Su and Kevin Duh and Xavier Carreras",
    booktitle = "Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing",
    publisher = "Association for Computational Linguistics",
    address = "United States",

    }

    Anand, P & Hardt, D 2016, Antecedent Selection for Sluicing: Structure and Content. in J Su, K Duh & X Carreras (eds), Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Austin, pp. 1234-1243, Austin, United States, 01/11/2016.

    Antecedent Selection for Sluicing : Structure and Content. / Anand, Pranav; Hardt, Daniel.

    Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. ed. / Jian Su; Kevin Duh; Xavier Carreras. Austin : Association for Computational Linguistics, 2016. p. 1234-1243.

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

    TY - GEN

    T1 - Antecedent Selection for Sluicing

    T2 - Structure and Content

    AU - Anand,Pranav

    AU - Hardt,Daniel

    PY - 2016

    Y1 - 2016

    N2 - 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.

    AB - 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.

    M3 - Article in proceedings

    SP - 1234

    EP - 1243

    BT - Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

    PB - Association for Computational Linguistics

    CY - Austin

    ER -

    Anand P, Hardt D. Antecedent Selection for Sluicing: Structure and Content. In Su J, Duh K, Carreras X, editors, Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Austin: Association for Computational Linguistics. 2016. p. 1234-1243.