Content Integration in Digital Libraries

摘要

With increasing amount of digitized content, it is possible now for digital libraries to provide ambient information rather than simple query results. This paper presents a content integration method that extracts semi-structured information from textbooks and integrates relevant content based on the relations extracted. We apply the method on a specified domain, traditional Chinese medicine (TCM), and operate on an operational public digital library, China America Digital Academic Library (CADAL). The extraction focuses on core TCM entities (herbal medicines, prescriptions, medical masters etc.) and their detailed properties. After that, we establish basic relations of different entities with domain ontology and resource metadata. Besides, latent relations, which describe semantic correlations, are also discovered via an entity parameterization procedure. Finally, integration is performed according to the relations discovered. A system is presented to show the encouraging improvement and library experience. Our method is a practical exploration to integrate digital resources and to promote library services in a feasible way.