An Empirically Motivated Algorithm for the Generation of Multimodal Referring Expressions

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

    86 Downloads (Pure)


    We describe an algorithm for generating
    multimodal referring expressions,
    based on empirical data. The main
    novelties are (1) a decision to point
    based on both the efficiency of pointing
    (Fitt’s law) and the inefficiency of
    a full linguistic description, (2) the explicit
    tracking of the ’focus of attention’,
    and (3) a threedimensional notion
    of salience incorporating linguistic, focus
    and inherent salience.
    Original languageUndefined/Unknown
    Title of host publicationProceedings of the Student Research Workshop of the 39th Annual Meeting of the Association of Computational Linguistics (ACL'01)
    Place of PublicationToulouse France
    Number of pages6
    Publication statusPublished - 2001

    Cite this