What you saw is what you want: Using Cases to seed Information Retrieval.

. This paper presents a hybrid case-based reasoning (CBR) and information retrieval (IR) system, called SPIRE, that both retrieves documents from a full-text document corpus and from within individual documents, and locates passages likely to contain information about important problem-solving features of cases. SPIRE uses two case-bases, one containing past precedents, and one containing excerpts from past case texts. Both are used by SPIRE to automatically generate queries, which are then run by the INQUERY full-text retrieval engine on a large text collection in the case of document retrieval and on individual text documents for passage retrieval. 1 Introduction A good indication of what to look for in a new problem situation is often given by examples of what has worked in the past. This idea---the fundamental tenet of case-based reasoning---is applicable in information retrieval (IR) as well. We have employed this idea at two levels in a hybrid CBR-IR approach: 1. within a corpus..