Affective and Dynamic Beam Search for Story Generation

Tenghao Huang, Ehsan Qasemi, Bangzheng Li, He Wang, Faeze Brahman, Muhao Chen, Snigdha Chaturvedi

Submission Type: Regular Long Paper

Submission Track: Discourse and Pragmatics

Submission Track 2: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Keywords: Discourse Analysis, Sentiment Analysis, Affective Computing

TL;DR: This paper introduces a new tool for generating engaging narratives, the Affective Story Generator (AffGen), which enhances the appeal of stories by introducing 'intriguing twists'.

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, 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.

Submission Number: 5106