Abstract
Advancing text generation algorithms (e.g., GPT-3) have led to new kinds of human-AI story co-creation tools. However, it is difficult for authors to guide this generation and understand the relationship between input controls and generated output. In response, we introduce TaleBrush, a GPT-based tool that uses abstract visualizations and sketched inputs. The tool allows writers to draw out the protagonist's fortune with a simple and expressive interaction. The visualization of the fortune serves both as input control and representation of what the algorithm generated (a story with varying fortune levels). We hope this demonstration leads the community to consider novel controls and sensemaking interactions for human-AI co-creation.
Author supplied keywords
Cite
CITATION STYLE
Chung, J. J. Y., Kim, W., Yoo, K. M., Lee, H., Adar, E., & Chang, M. (2022). TaleBrush: Visual Sketching of Story Generation with Pretrained Language Models. In Conference on Human Factors in Computing Systems - Proceedings. Association for Computing Machinery. https://doi.org/10.1145/3491101.3519873
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
