Narrative Intelligence: Papers from the AAAI Fall Symposium
Michael Mateas and Phoebe Sengers, Cochairs
November 5-7, North Falmouth, Massachusetts
While narrative has long been a theme in AI, it has recently experienced a surge of popularity. Researchers in various subfields, including story generation and understanding, agent architecture, and interface agents, have taken independent forays into narrative, finding it a fruitful way to rethink some basic issues in AI. Strands of work in narrative intelligence (NI) include the following:
Models of human narrative cognition: Since narrative is an important part of the way humans understand the world and each other, some researchers are looking at ways in which artificial agents can have similar narrative capabilities.
Architectures for generating narratively understandable behavior: Some researchers are building story-telling systems, interactive fiction architectures, and autonomous agents and interface agents, which can generate narratively structured behavior.
Meta-studies of narrative as part of AI research: AI researchers, being human, themselves use narrative to understand their own work. An understanding of this narrative process can improve the quality and social applicability of AI technology.
Within AI, this symposium includes work in areas such as story un-derstanding, story generation, interactive drama, narrative structure in interface design, narrative structure in the design of autonomous agents, believable agents (insofar as they participate in narrative structure), and interactive story-telling. In addition, because NI researchers have drawn deep inspiration from concepts of narrative from other disciplines, several papers from other research traditions, including narrative theory, art, and cultural studies were also included.