Affective and Dynamic Beam Search for Story Generation
This work addresses the need for more engaging story generation in applications like entertainment and education, though it appears incremental as it builds on existing beam search methods with novel tweaks.
The paper tackled the problem of generating interesting narratives by introducing AffGen, which uses Dynamic Beam Sizing and Affective Reranking to create 'intriguing twists' in stories, resulting in superior performance over baselines in generating affectively charged narratives as shown in empirical evaluations.
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, both automatic and human, demonstrate AffGen's superior performance over existing baselines in generating affectively charged and interesting narratives. Our ablation study and analysis provide insights into the strengths and weaknesses of AffGen.