David Leake

Many theories of explanation evaluation are based on context‐independent criteria. Such theories either restrict their consideration to explanation towards a fixed goal, or assume that all valid explanations are equivalent, so that evaluation criteria can be neutral to the goals underlying the attempt to explain. However, explanation can serve a range of purposes that place widely divergent requirements on the information an explanation must provide. It is argued that understanding what determines explanations' goodness requires a dynamic theory of evaluation, based on analysis of the information needed to satisfy the many goals that can prompt explanation; this view conforms to the commonsense idea that people accept and apply explanations precisely if those explanations give the information they need. A range of goals that can underly explanation is examined, and a theory is presented for evaluating whether an explanation provides the information an explainer needs for these goals. The theory is illustrated by sketching its implementation in the computer program, ACCEPTER, which does goal‐based evaluation of the goodness of explanations for surprising events in news stories.

Psychology and philosophy have long studied the nature and role of explanation. More recently, artificial intelligence research has developed promising theories of how explanation facilitates learning and generalization. By using explanations to guide learning, explanation-based methods allow reliable learning of new concepts in complex situations. This volume addresses fundamental issues in generating and judging explanations: When to explain, what constitutes an explanation, how to build explanations, and how to evaluate candidate explanations. It argues that standard models, which are neutral to context and experience, are inadequate to deal with the problems that arise in everyday explanation. It presents an alternative theory in which context---involving explainer beliefs, goals and experience---is crucial in generating and judging explanations. It examines the role of anomalies in motivating explanation, describes a model of pattern-based anomaly detection, and shows how an analysis of the content of anomalies, explanations, and explanation purposes can be used to guide generation and evaluation of explanations by a case-based explanation system. The theory is implemented in ACCEPTER, a computer system that understands stories, detects anomalous events, guides retrieval and adaptation of stored explanations, and evaluates candidate explanations.

In some views of cognitive science, episodic memory is simply one of many pieces of the puzzle of cognition: MEMORY, REASONING, and learning can be studied largely independently of one another. The case‐based reasoning (CBR) stance takes the contrasting position that human reasoning, memory, and learning are inextricably bound together. In this view, reasoning is primarily based on remembering and reapplying the lessons of prior episodes. A case‐based problem‐solver, for example, solves new problems by retrieving traces of relevant prior problems from memory, establishing correspondences between those problems and the new situation, and adapting the prior solutions to fit the problem at hand. Learning is a natural side effect of this process, as traces of new episodes are stored for future use.