Learning composite concepts in description logics: A first step
This paper proposes the use of description logics as a representational framework for learning composite concepts. Description logics are restricted variants of first-order logic providing a form of logical bias that dates back to semantic networks. Some recent work investigates concept learning in the context of these formalisms. Also, having recognized the importance of part-whole hierarchies in commonsense reasoning, researchers have started to incorporate part-of reasoning into description logics. In our approach we represent composite concepts in such a formalism. On one hand we have a relatively rich representation language with an infinite space of possible concepts. On the other hand we have special constructs for handling part-of relations that can be used in the learning algorithm to reduce the overall search space.
Unable to display preview. Download preview PDF.
- 1.Borgida, A., Brachman, R.J., McGuinness, D.L., Resnick, ‘CLASSIC: A Structural Data Model for Objects', Proceedings of SIGMOD 89, pp 59–67, 1989.Google Scholar
- 2.Cohen, W., Borgida, A., Hirsh, H., ‘Computing Least Common Subsumers in Description Logics', Proceedings of AAAI 92, pp 754–760, 1992.Google Scholar
- 3.Cohen, W., Hirsh, H., ‘Learning the CLASSIC Description Logic: Theoretical and Experimental Results', Principles of Knowledge Representation and Reasoning: Proceedings of the Fourth International Conference — KR 94, pp 121–133, 1994.Google Scholar
- 4.Cohen, W., Hirsh, H., ‘The Learnability of Description Logics with Equality Constraints', Machine Learning, Vol 17, pp 169–199, 1994.Google Scholar
- 5.Donini, F., Era, A., ‘Most Specific Concepts Technique for Knowledge Bases with Incomplete Information', Proceedings of the First International Conference on Information and Knowledge Management, pp 545–551, 1992.Google Scholar
- 6.Franconi, E., ‘A Treatment of Plurals and Plural Qualifications based on a Theory of Collections', Minds and Machines, Vol 3(4), pp 453–474, 1993.Google Scholar
- 7.Kietz, J.-U., Morik, K., ‘A Polynomial Approach to the Constructive Induction of Structural Knowledge', Machine Learning, Vol 14, pp 193–217, 1994.Google Scholar
- 8.Mitchell, T., ‘Generalization as Search', Artificial Intelligence, Vol 18(2), pp 203–226, 1982.Google Scholar
- 9.Nebel, B., Reasoning and Revision in Hybrid Representation Systems, Lecture Notes in Artificial Intelligence, 422, Springer-Verlag, 1990.Google Scholar
- 10.Padgham, L., Lambrix, P., ‘A Framework for Part-Of Hierarchies in Terminological Logics', Principles of Knowledge Representation and Reasoning: Proceedings of the Fourth International Conference — KR 94, pp 485–496, 1994.Google Scholar
- 11.Schaerf, A., ‘Which Semantics for Individuals in the Tbox?', Proceedings of the International Workshop on Description Logics, pp 5–8, 1994.Google Scholar
- 12.Speel, P.-H., Patel-Schneider, P., ‘CLASSIC extended with physical whole-part relations', Proceedings of the International Workshop on Description Logics, pp 45–50, 1994.Google Scholar