Enhancing Case Adaptation with Introspective Reasoning and Web Mining
David Leake, Jay Powell
Case-based problem-solving systems reason by retrieving relevant prior cases and adapting their solutions to fit new circumstances. The ability of case-based reasoning (CBR) to reason from ungeneralized episodes can benefit knowledge acquisition, but acquiring the needed case adaptation knowledge has proven challenging. This paper presents a method for alleviating this problem with just-in-time gathering of case adaptation knowledge, based on introspective reasoning and mining of Web knowledge sources. The paper highlights two facets of the system aimed at increasing the method's generality and its ease of application to new domains: Introspective reasoning to guide recovery from adaptation failures and reinforcement learning to guide selection of knowledge sources. The methods are tested in three highly different domains with encouraging results. The paper closes with a discussion of limitations and future steps.