Mike Brown, Christiane Förtsch, and Dieter Wissmann
This paper considers the type of problem for which the potential for amalgamating Information Retrieval (IR) and Case-Based Reasoning (CBR) technologies is the highest. IR is characterised as a bottom-up approach to retrieval of text within unconstrained domains. CBR is characterised as a top-down approach to retrieval of formalised information within domain-specific applications. It is argued that applications that require relatively detailed responses to specific queries of a large-scale, but domain specific text-based archive represent the middle ground between these two disjoint technologies - this is illustrated with a worked example.