Concept Learning

One of the bottlenecks of the ontology construction process is the amount of work required with various figures playing a role in it: domain experts contribute their knowledge that has to be formalized by knowledge engineers so that it can be mechanized. As the gap between these roles likely makes the process slow and burdensome, this problem may be tackled by resorting to machine learning tech- niques. By adopting algorithms from inductive logic programming, the effort of the domain expert can be reduced, i.e. he has to label individual resources as instances of the target concept. From those labels, axioms can be induced, which can then be confirmed by the knowledge engineer. In this chapter, we survey existing methods in this area and illustrate three different algorithms in more detail. Some basics like refinement operators, decision trees and information gain are described. Finally, we briefly present implementations of those algorithms