Comparing Cognitive and Computational Models of Narrative Structure

A growing number of applications seek to incorporate automatically generated narrative structure into interactive virtual environments. In this paper, we evaluate a representation for narrative structure generated by an automatic planning system by 1) mapping the plans that control plot into conceptual graphs used by QUEST, an existing framework for question-answering analysis that includes structures for modeling a reader's narrative comprehension and 2) using methods originally employed by QUEST’s developers to determine if the plan structures can serve as effective models of the understanding that human users form after viewing corresponding stories played out within a virtual world. Results from our analysis are encouraging, though additional work is required to expand the plan language to cover a broader class of narrative structure.