Contextual understanding depends on a reader's ability to correctly infer a context within which to interpret the events in a story. This "context-selection problem" has traditionally been expressed in terms of heuristics for making the correct initial selection of a story context. This paper presents a view of context selection as an ongoing process spread throughout the understanding process. This view requires that the understander be capable of recognizing and correcting erroneous initial context inferences, A computer program called ARTHUR is described, which selects the correct context for a story by dynamically re-evaluating its own initial inferences in light of subsequent information in a story.

In the course of understanding a text, a succession of decision points arise at which readers are faced with the task of choosing among alternative possible interpretations of what they're reading. Careful analysis of a wide range of sample texts reveals that such decisions are often based on complex evaluations of the interpretation being constructed, and sometimes cause the reader to construct and discard a number of intermediate inferences before settling on a final interpretation for a text.

This paper introduces Judgmental Inference theory as a proposed scheme of evaluation metrics and mechanisms, derived from examination of inference decisions arising during text understanding. A series of programs, ARTHUR, MACARTHUR and JUDGE are described, which incorporate some of the metrics and mechanisms of Judgmental Inference, enabling them to understand texts more complex than those that can be handled by other understanding systems.

Incremental learning from examples in a noisy domain is a difficult problem in Machine Learning. In this paper we divide the task into two subproblems and present a combination of numeric and symbolic approaches that yields robust learning of boolean characterizations. Our method has been implemented in a computer program, and we plot its empirical learning performance in the presence of varying amounts of noise.