Learning Probabilistic Ontologies with Distributed Parameter Learning

We consider the problem of learning both the structure and the parameters of Probabilistic Description Logics under DISPONTE. DISPONTE (DIstribution Semantics for Probabilistic ONTologiEs) adapts the distribution semantics for Probabilistic Logic Programming to Description Logics. The system LEAP for "LEArning Probabilistic description logics" learns both the structure and the parameters of DISPONTE knowledge bases (KBs) by exploiting the algorithms CELOE and EDGE. The former stands for "Class Expression Learning for Ontology Engineering" and it is used to generate good candidate axioms to add to the KB, while the latter learns the probabilistic parameters and evaluates the KB. EDGE for "Em over bDds for description loGics paramEter learning" is an algorithm for learning the parameters of probabilistic ontologies from data. In order to contain the computational cost, a distributed version of EDGE called EDGEMR was developed. EDGEMR exploits the MapReduce (MR) strategy by means of the Message Passing Interface. In this paper we propose the system LEAPMR. It is a re-engineered version of LEAP which is able to use distributed parallel parameter learning algorithms such as EDGEMR