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.
@article{arxiv.1811.03423,
title = {dAIrector: Automatic Story Beat Generation through Knowledge Synthesis},
author = {Markus Eger and Kory W. Mathewson},
journal= {arXiv preprint arXiv:1811.03423},
year = {2018}
}
Comments
10 pages with references, 1 figure. Accepted at Joint Workshop on Intelligent Narrative Technologies and Intelligent Cinematography and Editing at AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE'18). Edmonton, Alberta, Canada