Learning to Write Stories with Thematic Consistency and Wording Novelty


  • Juntao Li Peking University
  • Lidong Bing Tencent AI Lab
  • Lisong Qiu Peking University
  • Dongmin Chen Peking University
  • Dongyan Zhao Peking University
  • Rui Yan Peking University




Automatic story generation is a challenging task, which involves automatically comprising a sequence of sentences or words with a consistent topic and novel wordings. Although many attention has been paid to this task and prompting progress has been made, there still exists a noticeable gap between generated stories and those created by humans, especially in terms of thematic consistency and wording novelty. To fill this gap, we propose a cache-augmented conditional variational autoencoder for story generation, where the cache module allows to improve thematic consistency while the conditional variational autoencoder part is used for generating stories with less common words by using a continuous latent variable. For combing the cache module and the autoencoder part, we further introduce an effective gate mechanism. Experimental results on ROCStories and WritingPrompts indicate that our proposed model can generate stories with consistency and wording novelty, and outperforms existing models under both automatic metrics and human evaluations.




How to Cite

Li, J., Bing, L., Qiu, L., Chen, D., Zhao, D., & Yan, R. (2019). Learning to Write Stories with Thematic Consistency and Wording Novelty. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 1715-1722. https://doi.org/10.1609/aaai.v33i01.33011715



AAAI Technical Track: Game Playing and Interactive Entertainment