Stylized Story Generation with Style-Guided Planning
This work addresses the need for controllable text generation in storytelling systems, though it appears incremental as it builds on existing story generation tasks.
The paper tackles the problem of generating stories with a specified narration style, proposing a model that plans stylized keywords first and then generates the story guided by those keywords, achieving controllable generation of emotion-driven or event-driven stories on the ROCStories dataset.
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.