作者: Nicola Fanizzi , Claudia d’Amato , Floriana Esposito
DOI: 10.1007/978-3-642-15880-3_34
关键词:
摘要: A new framework for the induction of logical decision trees is presented. Differently from original setting, tests at tree nodes are expressed with Description Logic concepts. This has a number advantages: expressive terminological languages endowed full negation, thus allowing more natural division individuals each test node; these logics support standard ontology representing knowledge bases in Semantic Web. top-down method inducing proposed as an adaptation well-known tree-induction methods. offers alternative way learning concept descriptions can be associated to trees. version System TermiTIS, implementing methods, experimentally evaluated on ontologies popular repositories.