Version 2 2024-06-13, 14:55Version 2 2024-06-13, 14:55
Version 1 2023-02-03, 03:15Version 1 2023-02-03, 03:15
conference contribution
posted on 2023-02-03, 03:15authored byTed Goranson
We are designing a system to model narrative structures as expressed in lightly formalized text-centric chunks. The system is novel in shifting much of the organizational complexity to a categoric reasoning system in a two sorted logic. We optimize for two goals. One goal is to grow a pool of stored insights concerning complex narrative constructions, learned by aggregating crowd-sourced insights. These emphasize qualities that escape capture by existing methods, and include deliberate ambiguities, poetic allusions, irony, self reference, dynamic reinterpretation and cinematic devices. A second goal, described here, is to present suggested, machine generated narrative paths for an unskilled user, generated on the y and informed by developing insights of multiple narrative situations. The narrative paths may follow the target video's narrative, annotative machine constructed essays or some synthesis of these.