Query Translation for Mediators over Ontology-Based Information Sources
SETN '02 Proceedings of the Second Hellenic Conference on AI: Methods and Applications of Artificial Intelligence
Mediators over taxonomy-based information sources
The VLDB Journal — The International Journal on Very Large Data Bases
| Hi-index | 0.00 |
Abstract: Our research presented in this paper concerns the problem of fusing the results returned by the underlying systems to a mediating retrieval system, also called meta-retrieval system, meta-search engine, or mediator. We propose a fusion technique which is based solely on the actual results returned by each system for each query. The final (fused)ordering of documents is derived by aggregating the orderings of each system in a democratic manner. In addition, the fused ordering s accompanied by a level of democracy (alternatively construed as the level of confidence). Our method does not require any prior knowledge about the underlying systems, therefore it is appropriate for environments where the underlying systems are heterogeneous and autonomous, thus our method s appropriate for the web.