A Computational Model of Inferencing in Narrative
James Niehaus, R. Michael Young · 2009
Recent work in the area of interactive narrative has sought to develop systems that automatically produce experiences for a user that are understood as stories. Much of this work, however, has focused on the structural aspects of narrative rather than the process of narrative comprehension under-taken by users. Motivated by approaches in natural language discourse generation where explicit models of a reader’s men-tal state are often used to select and organize content in multi-sentential text, the work described here seeks to build an ex-plicit model of a reader’s inferencing process when reading (or participating in) a narrative. In this paper, we present a method for generating causal and intentional inferences, in the form of sequences of events, from a narrative discourse. We define a representation for the discourse, the sequence of discourse content, and show how it may be translated to a story representation, the reader’s plan. We define cognitive criteria of necessitated inferences with regards to these rep-resentations, and show how a partial order planner can deter-mine which inferences are enabled. The inference generation is motivated by findings in cognitive studies of discourse pro-cessing, and we provide support for their online generation by readers in a pilot study.