A SemiAutomatic Semantic Annotation and Authoring Tool for a Library Help Desk Service

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.