Affective and Dynamic Beam Search for Story Generation

arXiv:2310.15079v1 Announce Type: cross
Abstract: Storytelling's captivating potential makes it a fascinating research area, with implications for entertainment, education, therapy, and cognitive studies. In this paper, we propose Affective Story Generator (AffGen) for generating interesting narratives. AffGen introduces "intriguing twists" in narratives by employing two novel techniques-Dynamic Beam Sizing and Affective Reranking. Dynamic Beam Sizing encourages less predictable, more captivating word choices using a contextual multi-arm bandit model. Affective Reranking prioritizes sentence candidates based on affect intensity. Our empirical evaluations, …

abstract arxiv cognitive cs.ai cs.cl cs.lg dynamic education entertainment generator novel paper research search story storytelling studies therapy type