A minimum message length approach for argument interpretation

Ingrid Zukerman, Sarah George

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    3 Citations (Scopus)

    Abstract

    We describe a mechanism which receives as input a segmented argument composed of NL sentences, and generates an interpretation. Our mechanism relies on the Minimum Message Length Principle for the selection of an interpretation among candidate options. This enables our mechanism to cope with noisy input in terms of wording, beliefs and argument structure; and reduces its reliance on a particular knowledge representation. The performance of our system was evaluated by distorting automatically generated arguments, and passing them to the system for interpretation. In 75% of the cases, the interpretations produced by the system matched precisely or almost-precisely the representation of the original arguments.

    Original languageEnglish
    Title of host publicationThird SIGdial Workshop on Discourse and Dialogue: Proceedings of the Workshop
    EditorsK Jokinen, S McRoy
    Place of PublicationNew Brunswick USA
    PublisherAssociation for Computational Linguistics (ACL)
    Pages211-220
    Number of pages10
    Publication statusPublished - 2002
    EventSIGdial Workshop on Discourse and Dialog 2002 - Philadelphia, United States of America
    Duration: 11 Jul 200212 Jul 2002
    Conference number: 3rd

    Conference

    ConferenceSIGdial Workshop on Discourse and Dialog 2002
    Abbreviated titleSIGDIAL 2002
    Country/TerritoryUnited States of America
    CityPhiladelphia
    Period11/07/0212/07/02

    Cite this