Abstract. In geospatial applications with heterogeneous classification schemes that describe related domains, an ontology-driven approach to data sharing and interoperability relies on the alignment of concepts across different ontologies. To enable scalability both in the size and the number of the ontologies involved, the alignment method should be automatic. In this paper, we propose two fully automatic alignment methods that use the structure of the ontology graphs for contextual information, thus providing the matching process with more semantics. We have tested our methods on a set of geospatial ontologies pertaining to the domain of wetlands and on four sets that belong to an ontology repository that is becoming the standard for testing ontology alignment techniques. We have compared the effectiveness and efficiency of the proposed methods against two previous approaches. The effectiveness results that we have obtained with at least one of the new methods are as good or better than the results obtained with the previously proposed methods. 1

The problem of aligning ontologies and database schemas across different knowledge bases and databases is fundamental to knowledge management problems, including the problem of integrating the disparate knowledge sources that form the semantic web’s Linked Data [5]. We present a novel approach to this ontology alignment problem that employs a very large natural language text corpus as an interlingua to relate different knowledge bases (KBs). The result is a scalable and robust method (PID-GIN 1) that aligns relations and categories across different KBs by analyzing both (1) shared relation instances across these KBs, and (2) the verb phrases in the text instantiations of these relation instances. Experiments with PIDGIN demonstrate its superior performance when aligning ontologies across large existing KBs including NELL, Yago and Freebase. Furthermore, we show that in addition to aligning ontologies, PIDGIN can automatically learn from text, the verb phrases to identify relations, and can also type the arguments of relations of different KBs.