Hereby, we announce the availability of DL-Learner Build 2008-02-18, the second DL-Learner release. DL-Learner is a tool for learning complex classes from examples and background knowledge. It extends Inductive Logic Programming to Description Logics and the Semantic Web.
Downloads are available at the sf.net project page. For a list of the most important changes since the last release (Build 2007-08-31), see the Changelog. Most notably, DL-Learner now has a flexible component based design, which allows to extend it easily with new learning algorithms, learning problems, reasoners, and supported background knowledge sources. A new type of supported knowledge sources are SPARQL endpoints, from which DL-Learner can extract knowledge fragments, which enables learning classes even on large knowledge sources like DBpedia. Furthermore, DL-Learner now supports learning from positive examples only, inclusion axiom learning, the usage of N-Triple files as background knowledge, the OWL API reasoner interface, and has a more powerful web service interface. I’d like to thank Sebastian Hellmann, Sebastian Knappe, and Tilo Hielscher for their support.