Argument interpretation using Minimum Message Length

Sarah George, Ingrid Zukerman

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

    Abstract

    We describe an argument interpretation mechanism which receives as input a segmented argument composed of Natural Language sentences, and employs the Minimum Message Length Principle to select an interpretation among candidate options. This principle enables our mechanism to cope with noisy input in terms ofwording, beliefs and argument structure.The performance of our system was evaluated by distorting automatically generated arguments, and passing them to the system for interpretation. Our evaluation showed that in most cases, the interpretations produced by the system matched precisely or almost-precisely the representation of the original arguments.
    Original languageEnglish
    Title of host publicationAI 2002: Advances in Artificial Intelligence
    Subtitle of host publication15th Australian Joint Conference on Artificial Intelligence Canberra, Australia, December 2-6, 2002 Proceedings
    EditorsBob McKay, John Slaney
    Place of PublicationBerlin Germany
    PublisherSpringer
    Pages297-308
    Number of pages12
    ISBN (Print)3540001972
    DOIs
    Publication statusPublished - 2002
    EventAustralasian Joint Conference on Artificial Intelligence 2002 - Canberra, Australia
    Duration: 2 Dec 20026 Dec 2002
    Conference number: 15th
    https://link.springer.com/book/10.1007/3-540-36187-1 (Proceedings)

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer
    Volume2557
    ISSN (Print)0302-9743

    Conference

    ConferenceAustralasian Joint Conference on Artificial Intelligence 2002
    Abbreviated titleAI 2002
    CountryAustralia
    CityCanberra
    Period2/12/026/12/02
    Internet address

    Cite this