Title :
A method for organizing knowledge bases in the hierarchical form
Author_Institution :
Japan Adv. Inst. of Sci. & Technol., Ishikawa, Japan
Abstract :
We propose OSHAM, a novel top-down, unsupervised concept formation method based on a set-theoretic model for conceptual hierarchies. The method is close to the human approach to hierarchical classification and empirical results state its high ability to correctly classify new objects
Keywords :
knowledge based systems; knowledge engineering; set theory; unsupervised learning; OSHAM; conceptual hierarchies; hierarchical classification; hierarchical form; human approach; knowledge base organisation; object classification; set-theoretic model; unsupervised concept formation method; Classification tree analysis; Humans; Lattices; Learning systems; Organizing; Sparse matrices;
Conference_Titel :
Tools with Artificial Intelligence, 1994. Proceedings., Sixth International Conference on
Conference_Location :
New Orleans, LA
Print_ISBN :
0-8186-6785-0
DOI :
10.1109/TAI.1994.346394
