Stylized Story Generation with Style-Guided Planning

TL;DR

This paper introduces a new task of stylized story generation with style-guided planning, proposing a model that first plans style keywords and then generates stories, demonstrating controllable generation of emotion- and event-driven stories.

Contribution

The paper presents a novel generation model that incorporates style-guided planning for controllable story generation, along with automatic metrics for style consistency evaluation.

Findings

Model effectively controls story style based on specified keywords.

Experiments show successful generation of emotion- and event-driven stories.

Provides insights for future research in stylized story generation.

Abstract

Current storytelling systems focus more ongenerating stories with coherent plots regard-less of the narration style, which is impor-tant for controllable text generation. There-fore, we propose a new task, stylized story gen-eration, namely generating stories with speci-fied style given a leading context. To tacklethe problem, we propose a novel generationmodel that first plans the stylized keywordsand then generates the whole story with theguidance of the keywords. Besides, we pro-pose two automatic metrics to evaluate theconsistency between the generated story andthe specified style. Experiments demonstratesthat our model can controllably generateemo-tion-driven orevent-driven stories based onthe ROCStories dataset (Mostafazadeh et al.,2016). Our study presents insights for stylizedstory generation in further research.