Decision-Theoretic Resource Selection for Different Data Types in MIND

In a federated digital library system, it is too expensive to query every accessible library. Resource selection is the task to decide to which libraries a query should be routed. In this paper, we describe a novel technique that is used in the MIND project. Our approach, decision-theoretic framework (DTF), differs from existing algorithms like CORI in two ways: It computes a selection which minimises the overall costs (e.g. retrieval quality, time, money) of the distributed retrieval. And it allows for other data types beside text (e.g., names, years, images), whereas other resource selection techniques are restricted to text.

• Type: Conference
• Year: 2003
• Where: SIGIR
• Authors: Henrik Nottelmann, Norbert Fuhr
• Keywords: Federated Digital Library, Resource Selection, Resource Selection Techniques, SIGIR 2003