Abstract
The ability to generate narrative is of importance to
computer systems that wish to use story effectively
for entertainment, training, or education. One way
to generate narrative is to use planning. However,
story planners are limited by the fact that they can
only operate on the story world provided, which
impacts the ability of the planner to find a solution
story plan and the quality and structure of the story
plan if one is found. We present a planning
algorithm for story generation that can nondeterministically
make decisions about the
description of the initial story world state in a leastcommitment
fashion.
Users
Please
log in to take part in the discussion (add own reviews or comments).