CODI: Combinatorial Optimization for Data Integration: results for OAEI 2011

Jakob Huber, Timo Sztyler, Jan Nößner, Christian Meilicke
2011 International Semantic Web Conference  
In this paper, we describe our probabilistic-logical alignment system CODI (Combinatorial Optimization for Data Integration). The system provides a declarative framework for the alignment of individuals, concepts, and properties of two heterogeneous ontologies. CODI leverages both logical schema information and lexical similarity measures with a well-defined semantics for A-Box and T-Box matching. The alignments are computed by solving corresponding combinatorial optimization problems. 1
more » ... ation of the system 1.1 State, purpose, general statement CODI (Combinatorial Optimization for Data Integration) leverages terminological structure for ontology matching. The current implementation produces mappings between concepts, properties, and individuals. The system combines lexical similarity measures with schema information to completely avoid incoherence and inconsistency during the alignment process. CODI participates in 2011 for the second time in an OAEI campaign. Thus, we put a special focus on differences compared to the previous 2010 version of CODI. Specific techniques used CODI is based on the syntax and semantics of Markov logic [2] and transforms the alignment problem to a maximum-a-posteriori optimization problem. This problem needs a-priori confidence values for each matching hypotheses as input. Therefore, we implemented an aggregation method of different similarity measures. Another new feature of CODI is the recognition of ontology pairs belonging to different versions of the same ontology. In instance matching CODI does not compute lexical similarities for all existing pairs of instances but utilizes object-property assertions for reducing the necessary comparisons.
dblp:conf/semweb/HuberSNM11 fatcat:6sixztfgfrhhfaovndnpcykkmy