Corpus-based metrics for assessing common ground

Roman Kutlak, Kees van Deemter, Christopher Mellish

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

Abstract

This article presents the first attempt to construct a computational model of common ground. Four corpus-based metrics are presented that estimate what facts are likely to be in common ground. The proposed metrics were evaluated in an experiment with human participants, focussing on a domain of famous people. The results are encouraging: two of the proposed metrics achieved a large positive correlation between the estimates of how widely known a property of a famous person is and the percentage of participants who knew the corresponding property.
Original languageEnglish
Title of host publicationProceedings of the 34th Annual Conference of the Cognitive Science Society
Place of PublicationSapporo, Japan
PublisherCognitive Science Society
Pages1834-1839
Number of pages6
ISBN (Print)978-0-9768318-8-4
Publication statusPublished - 2012

    Fingerprint

Keywords

  • corpus based metrics
  • community common ground

Cite this

Kutlak, R., van Deemter, K., & Mellish, C. (2012). Corpus-based metrics for assessing common ground. In Proceedings of the 34th Annual Conference of the Cognitive Science Society (pp. 1834-1839). Sapporo, Japan: Cognitive Science Society.