Knowledge Management (KM) has become the focus of a lot of scientific research during the second half of the twentieth century as researchers discovered the importance of the knowledge resource to business organizations. Recent research developed ontology-based knowledge management systems (KMS) to provide a standardized reference for knowledge consistency. However, use of ontologies has been impeded by the difficulties encountered in building ontologies, especially difficulties in the knowledge acquisition stage. It is hypothesized that NLP tools can be usefully implemented to assist in the knowledge acquisition stage for ontology building in specific, and to develop effective KMS's in general. The proposed system, CRISP, utilizes a shallow parser for extracting concept relations from construction contract documents to assist in the development of an ontology-based KMS. When compared with human evaluators, CRISP achieved almost 80% of the average kappa score attained by the evaluators, and approximately 90% of their F-measure score. |