Draft and Edit: Automatic Storytelling Through Multi-Pass Hierarchical Conditional Variational Autoencoder

Automatic Storytelling has consistently been a challenging area in the field of natural language processing. Despite considerable achievements have been made, the gap between automatically generated stories and human-written stories is still significant. Moreover, the limitations of existing automatic storytelling methods are obvious, e. g. , the consistency of content, wording diversity. In this paper, we proposed a multi-pass hierarchical conditional variational autoencoder model to overcome the challenges and limitations in existing automatic storytelling models. While the conditional variational autoencoder (CVAE) model has been employed to generate diversified content, the hierarchical structure and multipass editing scheme allow the story to create more consistent content. We conduct extensive experiments on the ROCStories Dataset. The results verified the validity and effectiveness of our proposed model and yields substantial improvement over the existing state-of-the-art approaches.

Authors

• Meng-Hsuan Yu
• Juntao Li Soochow University
• Danyang Liu University of Edinburgh
• Dongyan Zhao Wangxuan Institute of Computer Technology, Peking University National Key Laboratory of General Artificial Intelligence
• Rui Yan
• Bo Tang
• Haisong Zhang

Keywords

No keywords are indexed for this paper.