dAIrector: Automatic Story Beat Generation through Knowledge Synthesis
This addresses the understudied domain of long-form narrative creation for storytellers and performers, but appears incremental as it builds on existing human-machine collaboration concepts.
The paper tackles the problem of automated story beat generation for human-machine creative collaboration in narrative creation, presenting dAIrector, a system that assists in live improvisational performances and writing, with results including quantitative evaluation and qualitative feedback from a professional performer.
dAIrector is an automated director which collaborates with humans storytellers for live improvisational performances and writing assistance. dAIrector can be used to create short narrative arcs through contextual plot generation. In this work, we present the system architecture, a quantitative evaluation of design choices, and a case-study usage of the system which provides qualitative feedback from a professional improvisational performer. We present relevant metrics for the understudied domain of human-machine creative generation, specifically long-form narrative creation. We include, alongside publication, open-source code so that others may test, evaluate, and run the dAIrector.