Let Us Tell You a fAIble: Content Generation Through Graph-Based Cognition
Abstract
In this work we present fAlble: a novel graph-based modular storytelling framework. fAIble is centered around a graph database, incorporates invariable elements of folktale structure, while accounting for thoughts and actions. Action outcomes are a product of probabilistic story generation. Probabilities are based on elements of common sense, invariable elements of folktale structure, high-level character roles, and a wide variety of other variables (e.g. characters' physical and psychological traits, context-based likelihood of encountering specific items and characters, etc.). A prototype implementation is tested through an anonymous questionnaire. Results demonstrate the ability of graph-based cognition to produce coherent story prototypes with sensible character actions, while maintaining output variability.
Publication Date
1-1-2018
Publication Title
Proceedings of the 31st International Florida Artificial Intelligence Research Society Conference, FLAIRS 2018
Number of Pages
282-287
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
Copyright Status
Unknown
Socpus ID
85059602728 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85059602728
STARS Citation
Kazakova, Vera A.; Hastings, Lauren; Posadas, Andres; Gonzalez, Lucas C.; and Knauf, Rainer, "Let Us Tell You a fAIble: Content Generation Through Graph-Based Cognition" (2018). Scopus Export 2015-2019. 9553.
https://stars.library.ucf.edu/scopus2015/9553