Stylized Story Generation with Style-Guided Planning

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 2430–2436 August 1–6, 2021. ©2021 Association for Computational Linguistics 2430 Stylized Story Generation with Style-Guided Planning Xiangzhe Kong⇤, Jialiang Huang⇤, Ziquan Tung, Jian Guan and Minlie Huang† The CoAI group, DCST, Institute for Artificial Intelligence, State Key Lab of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China {kxz18,huang-jl17,tongzq18,j-guan19}@mails.tsinghua.edu.cn, aihuang@tsinghua.edu.cn Abstract Current storytelling systems focus more on generating 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 tackle the problem, we propose a novel generation model that first plans the stylized keywords and then generates the whole story with the guidance of the keywords. Besides, we pro- pose two automatic metrics to evaluate the consistency between the generated story and the specified style. Experiments demonstrates that our model can controllably generate emo- tion-driven or event-driven stories based on the ROCStories dataset (Mostafazadeh et al., 2016). Our study presents insights for stylized story generation in further research. 1 Introduction Story generation is a challenging task in natural language generation (NLG), namely generating a reasonable story given a leading context. Recent work focuses on enhancing the coherence of gen- erated stories (Fan et al., 2018; Yao et al., 2019) or introducing commonsense knowledge (Guan et al., 2020; Xu et al., 2020). However, it has not yet been investigated to generate stories with controllable styles, which is important since dif- ferent styles serve different writing purposes. As exemplified in Figure 1, emotion-driven stories use emotional words (e.g., “excited”, “enjoyed”) to reveal the inner states of the characters and bring the readers closer to the characters. In com- parison, event-driven stories usually contain a se- quence of events with a clear temporal order (e.g., “tearing”!“tried”!“found”!“hooked”), which aims to narrate the story objectively. ⇤Equal contribution. †Corresponding author. Emotion- driven Event- driven She got excited to have it. It was pretty for the extra large screen. After using, she was very satisfied with the sound and design. She didn't regret buying this TV. Leading Context: Alice bought a new television. The picture on screen was tearing. Then she tried different adjustments. Eventually, she found out what was wrong. She got the wrong cable hooked up. Style Story Figure 1: Example of stylized story generation given the same leading context. The stylized keywords are in bold. In this paper, we formalize the task of stylized story generation, which requires generating a co- herent story with a specified style given the first sentence as the leading context. Style has multi- ple interpretations, which can be seen as a unique voice of the author expressed through the use of cer- tain stylistic devices (e.g. choices of words)(Mou and Vechtomova, 2020). In this work we focus on the choices of words and define the story styles based on the …

Content truncated to 500 words