Characterisation of knowledge bases

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

Abstract

The process of determining the principal topic of a Knowledge base (KB), and whether it conforms to a set of user-defined constraints, are important steps in the reuse of Knowledge Bases. We refer to these steps as the process of characterization of a Knowledge Base. Identify-Knowledge-Base (IKB) is a tool, which suggests the principal topic(s) addressed by the Knowledge Base. It matches concepts extracted from a particular knowledge base against some reference taxonomy, where the taxonomy can be pre-stored or extracted from ontologies which are either stored on the local machine or are assessable through the WWW. The 'most specific' super-concept subsuming these concepts is said to be the principal topic of the knowledge base. Additionally, a series of filters, which check if a KB has particular characteristics have been implemented. This paper describes both the Identify-Knowledge Base system and these filters. Some empirical studies of IKB and the filters with a range of problems are also reported.

Original languageEnglish
Title of host publicationApplications and Innovations in Intelligent Systems XI
Subtitle of host publicationProceedings of Ai2003, the Twenty-Third Sgai International Conference on Innovative Techniques and Applications of Artificial Intelligence
EditorsMax Bramer, Richard Ellis, Ann Macintosh
PublisherSpringer-Verlag
Pages235-246
Number of pages12
ISBN (Print)9781852337797, 1852337796
Publication statusPublished - 2004

Publication series

NameBCS Conference Series
PublisherSpringer

Fingerprint

Dive into the research topics of 'Characterisation of knowledge bases'. Together they form a unique fingerprint.

Cite this