Learning Schemata for Natural Language Processing

This paper describes a natural language system which improves its own performance through learning. The system processes short English narratives and is able to acquire, f rom a single narrative, a new schema for a stereotypical set of actions. During the understanding process, the system attempts to construct explanations for characters' actions in terms of the goals their actions were meant to achieve. When the system observes that a character has achieved an interesting goal in a novel way, it generalizes the set of actions they used to achieve this goal into a new schema. The generalization process is a knowledge-based analysis of the causal structure of the narrative which removes unnecessary details whi le maintaining the val id i ty of the causal explanation. The resulting generalized set of actions is then stored as a new schema and used by the system to correctly process narratives which were previously beyond its capabilities.