This paper presents a comprehensive approach to automatic theory refinement. In contrast to other systems, the approach is capable of modifying a theory which contains multiple faults and faults which occur at intermediate points in the theory. The approach uses explanations to focus the corrections to the theory, with the corrections being supplied by an inductive component. In this way, an attempt is made to preserve the structure of the original theory as much as possible. Because the approach begins with an approximate theory, learning an accurate theory takes fewer examples than a purely inductive system. The approach has application in expert system development, where an initial, approximate theory must be refined. The approach also applies at any point in the expert system lifecycle when the expert system generates incorrect results. The approach has been applied to the domain of molecular biology and shows significantly better results then a purely inductive learner.
ML ID: 3
Abduction is an important inference process underlying much of human intelligent activities, including text understanding, plan recognition, disease diagnosis, and physical device diagnosis. In this paper, we describe some problems encountered using abduction to understand text, and present some solutions to overcome these problems. The solutions we propose center around the use of a different criterion, called explanatory coherence, as the primary measure to evaluate the quality of an explanation. In addition, explanatory coherence plays an important role in the construction of explanations, both in determining the appropriate level of specificity of a preferred explanation, and in guiding the heuristic search to efficiently compute explanations of sufficiently high quality.
ML ID: 2
This article discusses how explanation-based learning of plan schemata from observation can improve performance of plan recognition. The GENESIS program is presented as an implemented system for narrative text understanding that learns schemata and improves its performance. Learned schemata allow GENESIS to use schema-based understanding techniques when interpreting events and thereby avoid the expensive search associated with plan-based understanding. Learned schemata also function as new concepts that can be used to cluster examples and index events in memory. In addition. experiments are reviewed which demonstrate that human subjects, like GENESIS, can learn a schema by observing, explaining, and generalizing a single specific instance presented in a narrative.
ML ID: 1