Information Technology Reference
In-Depth Information
CHAPTER 1
Narrative Intelligence
Michael Mateas and Phoebe Sengers
Carnegie Mellon University, Pittsburgh, PA;
Cornell University, Ithaca, NY
Introduction
People are narrative animals. As children, our caretakers immerse us in stories:
fairy tales, made-up stories, favorite stories, “Read me a story!” Even when
barely verbal, we begin to tell our own proto-stories. As children, narrative
frameworks become an important part of the way we learn to approach the
world (Nelson 1989).
As adults, we continue to surround ourselves with stories, furnishing our
worlds not just with data but with meaning. We say to one another, “Have you
heard? Frank and Barb had a fight. She's sick of him letting the dog on the
bed. I always told him he'd get in trouble with his permissive ways with that
beast.” By telling stories we make sense of the world. We order its events and
find meaning in them by assimilating them to more-or-less familiar narratives.
It is this human ability to organize experience into narrative form that David
Blair and Tom Meyer call “Narrative Intelligence” (Blair & Meyer 1997) and
around which AI research into narrative coalesces.
A brief history of narrative intelligence
Given the primary importance of narrative in human experience, it is no sur-
prise that story and narrative have long been of interest to AI researchers. In
the 1970's and early 80's there was a substantial amount of interest in story
understanding and generation in particular. Work in this area was particularly
strong in Roger Schank's research group at Yale. Schank and his group explored
