GRAPH: The Costs of Redundancy in Referring Expressions

Emiel Krahmer, Mariet Theune, Jette Viethen, Iris Hendrickx

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

    10 Citations (Scopus)
    48 Downloads (Pure)


    We describe a graph-based generation system that participated in the TUNA attribute selection and realisation task of the REG 2008 Challenge. Using a stochastic cost function (with certain properties for free), and trying attributes from cheapest to more expensive, the system achieves overall .76 DICE and .54 MASI scores for attribute selection on the development set. For realisation, it turns out that in some cases higher attribute selection accuracy leads to larger differences between system-generated and human descriptions.
    Original languageUndefined
    Title of host publicationProceedings of the 5th International Natural Language Generation Conference (INLG 2008)
    Place of PublicationUSA
    PublisherAssociation for Computational Linguistics (ACL)
    Number of pages3
    ISBN (Print)not assigned
    Publication statusPublished - Jun 2008
    Event5th International Natural Language Generation Conference, INLG 2008 - Salt Fork, Ohio, USA
    Duration: 12 Jun 200814 Jun 2008

    Publication series

    PublisherThe Association for Computational Linguistics


    Conference5th International Natural Language Generation Conference, INLG 2008
    Other12-14 June 2008


    • EWI-13092
    • IR-64885
    • METIS-251092

    Cite this