Referring expression generation in interaction: a graph-based perspective

Emiel Krahmer, Martijn Goudbeek, Mariet Theune

    Research output: Chapter in Book/Report/Conference proceedingChapterAcademic

    Abstract

    Reference is important in everyday interactions: people can only exchange information about objects when they agree on how to refer to those objects. How this agreement may arise, and how we can model this in natural language generation, is the topic of this chapter. We argue that two possibly competing forces play a role. On the one hand, speakers may have inherent preferences for certain properties when referring to objects in a given domain. On the other, they may also have a tendency to adapt to the references produced by their dialogue partner. We describe how preferences can be determined, and how they interact with adaptation.
    Original languageUndefined
    Title of host publicationNatural Language Generation in Interactive Systems
    EditorsAmanda Stent, Srinivas Bangalore
    Place of PublicationCambridge, UK
    PublisherCambridge University Press
    Pages126-148
    Number of pages23
    ISBN (Print)978-1-107-01002-4
    DOIs
    Publication statusPublished - Jun 2014

    Publication series

    Name
    PublisherCambridge University Press

    Keywords

    • EWI-25530
    • METIS-309797
    • IR-94139

    Cite this