When Expectation Fails: Towards a Self-Correcting Inference System

Abstract

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.