A corpus-based approach to help-desk response generation

Ingrid Zukerman, Yuval Marom

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

    4 Citations (Scopus)

    Abstract

    We are developing a corpus-based approach for the prediction of help-desk responses from features in customers ' emails, where responses are represented at two levels of granularity: document and sentence. We present an automatic evaluation of the responses generated by our system, as well as a manual one involving human judges. The automatic evaluation involves textual comparisons between generated responses and responses composed by the help-desk operators. The results show that both levels of granularity produce good responses, addressing inquiries of different kinds. The human-based evaluation measures response informativeness, and confirms our conclusion that both levels of granularity produce useful responses.

    Original languageEnglish
    Title of host publicationCIMCA 2006
    Subtitle of host publicationInternational Conference on Computational Intelligence for Modelling, Control and Automation, Jointly with IAWTIC 2006: International Conference on Intelligent Agents Web Technologies ...
    DOIs
    Publication statusPublished - 1 Dec 2007
    EventCIMCA 2006: International Conference on Computational Intelligence for Modelling, Control and Automation, Jointly with IAWTIC 2006: International Conference on Intelligent Agents Web Technologies and International Commerce - Sydney, NSW, Australia
    Duration: 28 Nov 20061 Dec 2006

    Conference

    ConferenceCIMCA 2006: International Conference on Computational Intelligence for Modelling, Control and Automation, Jointly with IAWTIC 2006: International Conference on Intelligent Agents Web Technologies and International Commerce
    Country/TerritoryAustralia
    CitySydney, NSW
    Period28/11/061/12/06

    Cite this