A Semi-Automatic Semantic Annotation and Authoring Tool for a Library Help Desk Service

Antti Vehviläinen, Eero Hyvönen, Olli Alm

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

    3 Citations (Scopus)


    This paper discusses how knowledge technologies can be utilized in creating help desk services on the semantic web. To ease the content indexer's work, we propose semi-automatic semantic annotation of natural language text for annotating question-answer (QA) pairs, and case-based reasoning techniques for finding similar questions. To provide answers matching with the indexer's and end-user's information needs, methods for combining case-based reasoning with semantic search and browsing are proposed. We integrate different data sources by using large ontologies of upper common concepts, places, and agents. Techniques to utilize these sources in authoring answers are suggested. A prototype implementation of a real life ontology-based help desk application is presented as a proof of concept. This system is based on the data set of over 20,000 QA pairs and the operational principles of an existing national library help desk service in Finland.
    Original languageEnglish
    Title of host publicationProceedings of the first Semantic Authoring and Annotation Workshop (SAAW2006), Athens, GA, USA, November 6th 2006
    PublisherRWTH Aachen
    Publication statusPublished - 2006
    MoE publication typeA4 Article in a conference publication
    EventSemantic Authoring and Annotation Workshop - Athens, United States
    Duration: 6 Nov 20066 Nov 2006
    Conference number: 1

    Publication series

    NameCEUR Workshop Proceedings
    ISSN (Print)1613-0073


    WorkshopSemantic Authoring and Annotation Workshop
    CountryUnited States


    • case-based reasoning
    • help desk services
    • semantic annotation
    • semantic web

    Fingerprint Dive into the research topics of 'A Semi-Automatic Semantic Annotation and Authoring Tool for a Library Help Desk Service'. Together they form a unique fingerprint.

    Cite this