Capturing and Modeling Domain Knowledge Using Natural Language Processing Techniques

摘要

Command and control (C2) and the decision making domain are seriously threatened, facing information overload and uncertainty issues. To make sense out of the flood of information, military have to create new ways of processing sensor and intelligence information, and of providing the results to commanders. Initiated in 2004 at Defense Research and Development Canada (DRDC), the SACOT knowledge engineering research project is currently investigating, developing and validating innovative natural language processing (NLP) approaches as scientific means to capture knowledge objects contained in domain- specific electronic texts and turn them rapidly into broad domain ontologies to be used in third-party applications. Ontologies are key elements required to enable next generation of decision support and knowledge exploitation systems with new semantic capabilities. Major impediments to classic development of ontologies are that it is a time and budget consuming operation. It is also largely dependant on Subject Matter Experts (SME) own limitations. Exhaustive elicitation of knowledge objects of a domain requires the application of NLP extraction techniques over textual data. This paper illustrates how recent advances in NLP techniques are implemented in the SACOT framework to automate elicitation of knowledge objects from unstructured texts and to support efficiently SMEs in ontology engineering tasks.