PLOTSHOT: Generating Discourse-constrained Stories around Photos
In this paper, we propose a novel story generator, PLOTSHOT, capable of reasoning over discourse materials during fabula generation such that these materials meaningfully constrain the development of a causally and intentionally coherent story.
September 19, 2016
The Twelfth Annual AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 2016
Authors
Rogelio Cardona-Rivera (Disney Research/North Carolina State University)
Boyang Albert Li (Disney Research)
Story generators typically adopt a pipelined model of generation wherein fabula structure is decided independently and prior to discourse structure. In this paper, we propose a novel story generator, PLOTSHOT, capable of reasoning over discourse materials during fabula generation such that these materials meaningfully constrain the development of a causally and intentionally coherent story. PLOTSHOT incorporates user-supplied photographs as optional story states through an oversubscription planning paradigm. Further, to leverage existing work on planning-based models of generation, we present a technique to compile the photo story planning problem to classical narrative planning. Our system attempts to maximize quality of an illustrated story by analyzing the affinity between a photo and the action it is meant to depict. An evaluation of generated artifacts shows advantage over heuristic baseline techniques.