Towards the generation of rebuttals in a Bayesian argumentation system

Nathalie Jitnah, Ingrid Zukerman, Richard McConachy, Sarah George

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

    9 Citations (Scopus)

    Abstract

    We describe a mechanism which generates rebuttals to a user's rejoinders in the context of arguments generated from Bayesian networks. This mechanism is implemented in an interactive argumentation system. Given an argument generated by the system and an interpretation of a user's rejoinder, the generation of the rebuttal takes into account the intended effect of the user's rejoinder, determined on a model of the user's beliefs, and its actual effect, determined on a model of the system's beliefs. We consider three main rebuttal strategies: refute the user's rejoinder, strengthen the argument goal, and dismiss the user's line of reasoning.

    Original languageEnglish
    Title of host publicationProceedings of the First International Conference on Natural Language Generation (INLG'2000)
    EditorsMichael Elhadad
    Place of PublicationNew Jersey USA
    PublisherAssociation for Computational Linguistics (ACL)
    Pages39-46
    Number of pages8
    ISBN (Electronic)9659029608, 9789659029600
    ISBN (Print)9659029608
    Publication statusPublished - 2000
    EventInternational Natural Language Generation Conference 2000 - Mitzpe Ramon, Israel
    Duration: 12 Jun 200016 Jun 2000
    Conference number: 1st
    https://aclanthology.org/volumes/W00-14/ (Proceedings)

    Conference

    ConferenceInternational Natural Language Generation Conference 2000
    Abbreviated titleINLG 2000
    Country/TerritoryIsrael
    CityMitzpe Ramon
    Period12/06/0016/06/00
    Internet address

    Cite this