No abstract

No abstract

We consider an existing approach for mining general inclusion axioms written in a lightweight Description Logic. In comparison to classical association rule mining, this approach allows more complex patterns to be obtained. Ours is the first implementation of these algorithms for learning Description Logic axioms. We use our implementation for a case study on two real world datasets. We discuss the outcome and examine what further research will be needed for this approach to be applied in a practical setting.

No abstract

In a recent approach, Baader and Distel proposed an algorithm to axiomatize all terminological knowledge that is valid in a given data set and is expressible in the description logic EL K . This approach is based on the mathematical theory of formal concept analysis. However, this algorithm requires the initial data set to be free of errors, an assumption that normally cannot be made for real-world data. In this work, we propose a first extension of the work of Baader and Distel to handle errors in the data set. The approach we present here is based on the notion of confidence, as it has been developed and used in the area of data mining.