Our paper “Background Knowledge in Schema Matching: Strategy vs. Data” has been accepted at the 20th International Semantic Web Conference. The paper has been co-authored by Jan Portisch, Michael Hladik, and Heiko Paulheim.
In the paper, we have conducted a number of controlled experiments with using background knowledge in schema matching, altering both the source of background knowledge as well as the strategy for its exploitation. One of the key findings of the paper is that while the actual source of background knowledge used does not matter too much, there is a lot of potential in developing interesting exploitation strategies.
A preprint of the paper is available here.