A distributed information extraction system integrating ontological knowledge and probabilistic classifiers

In this work we consider the problem of extracting concepts and relations between them from documents, aiming at constructing an index for a more semantically oriented search engine. While assessment is performed on a biomedical application, the proposed solutions can be also applied to different domains. With the distributed architecture proposed, we obtain an approach that can be applied also on large data sets. Experimental assessment has been performed on a standard data set, BioNLP 2013.