Towards an Error-Tolerant Construction of EL -Ontologies from Data Using Formal Concept Analysis

In the work of Baader and Distel, a method has been proposed to axiomatize all general concept inclusions (GCIs) expressible in the de- scription logic EL and valid in a given interpretation I. This provides us with an effective method to learn EL -ontologies from interpretations. In this work, we want to extend this approach in the direction of handling errors, which might be present in the data-set. We shall do so by not only considering valid GCIs but also those whose confidence is above a given threshold c. We shall give the necessary definitions and show some first re- sults on the axiomatization of all GCIs with confidence at least c. Finally, we shall provide some experimental evidence based on real-world data that supports our approach.