Document Type

Conference Proceeding

Publication Date



Success in schema integration depends on understanding the semantics of schema components (e.g., entity sets, relationship sets, attributes), and the ability to capture and reason about these semantics. An important objective of our work on schema integration is to automate the reasoning as much as possible, and when not possible, depend on the human input and guidance. A key results of comparing the semantics associated with schema objects is that of determining attribute relationship. Once attribute relationships are determined, the task of object class(e.g., entity sets and relationship sets) integration becomes simpler and can e automated to a great extent. In our work, we use a classifier borrowed from the research in knowledge representation(particularly the KL-ONE family of systems) for automatically integrating objects classes.


Presented at the NSF Workshop on Heterogeneous Databases, December 1989.