Content Learning with Structure-Aware Writing: A Graph-Infused Dual Conditional Variational Autoencoder for Automatic Storytelling

Authors

  • Meng-Hsuan Yu Peking University
  • Juntao Li Soochow University
  • Zhangming Chan Peking University
  • Rui Yan Peking University
  • Dongyan Zhao Peking University

Keywords:

Game Design -- Procedural Content Generation & Storytelling

Abstract

Recent automatic storytelling methods mainly rely on keyword planning or plot skeleton generation to model long-range dependencies and create consistent narrative texts. However, these approaches generate story plans or plots sequentially, leaving the non-sequential conception and structural design processes of human writers unexplored. To mimic human writers and exploit the fine-grained, intrinsic structural information of each story, we decompose automatic story generation into sub-problems of graph construction, graph generation, and graph-infused sequence generation. Specifically, we propose a graph-infused dual conditional variational autoencoder model to capture multi-level intra-story structures (i.e., graph) by continuous variational latent variables and generate consistent stories through dual-infusion of story structure planning and content learning. Experimental results on the ROCStories dataset and the CMU Movie Summary corpus confirm that our proposed model outperforms strong baselines in both human judges and widely-used automatic metrics.

Downloads

Published

2021-05-18

How to Cite

Yu, M.-H., Li, J., Chan, Z., Yan, R., & Zhao, D. (2021). Content Learning with Structure-Aware Writing: A Graph-Infused Dual Conditional Variational Autoencoder for Automatic Storytelling. Proceedings of the AAAI Conference on Artificial Intelligence, 35(7), 6021-6029. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16751

Issue

Section

AAAI Technical Track on Humans and AI