Many applications in modern information technology utilize ontological knowledge to increase their performance, precision, and success rate. However, the integration of ontological sources is in general a difficult task since the semantics of all concepts, individuals, and relations must be preserved across the various sources. In this paper we discuss the importance of combined background knowledge for recognizing textual entailment (RTE). We present and analyze formally a new graph-based procedure for integration of concepts and individuals from ontologies based on the hierarchy of WordNet. We embed it in our experimental RTE framework where a deep-shallow semantic text analysis combined with logical inference is used to identify the logical relations between two English texts. Our results show that fine-grained and consistent knowledge coming from diverse sources is a necessary condition determining the correctness and traceability of results. The RTE application performs significantly better when a substantial amount of problemrelevant knowledge has been integrated into its inference process.
展开▼
