Case-based content navigation

摘要

This paper describes a document retrieval system called CAIRN that uses a case-based reasoning set using a large lexicon to automatically generate a case index to that document set. The index is used by a case-based retrieval engine to find documents. The retrieval engine is tolerant of noisy natural language queries. CAIRN also supports failure-driven learning of important concepts during its use and thus can significantly improve its retrieval accuracy over time. The limitations of this system are discussed.