Learning to Predict Explainable Plots for Neural Story Generation

Abstract

Story generation is an important natural language processing task that aims to generate coherent stories automatically. While the use of neural networks has proven effective in improving story generation, how to learn to generate an explainable high-level plot still remains a major challenge. In this work, we propose a latent variable model for neural story generation. The model treats an outline, which is a natural language sentence explainable to humans, as a latent variable to represent a high-level plot that bridges the input and output. We adopt an external summarization model to guide the latent variable model to learn how to generate outlines from training data. Experiments show that our approach achieves significant improvements over state-of-the-art methods in both automatic and human evaluations.

10 pages

References in corpus (7)

• Auto-Encoding Variational Bayes
• Narrative Planning: Balancing Plot and Character
• Neural Variational Inference and Learning in Belief Networks
• Story Generation from Sequence of Independent Short Descriptions
• A Tutorial on Deep Latent Variable Models of Natural Language
• Paper Abstract Writing through Editing Mechanism
• Hierarchical Text Generation using an Outline

Cited by in corpus (5)

• Neural Language Generation: Formulation, Methods, and Evaluation
• Content Planning for Neural Story Generation with Aristotelian Rescoring
• Consistency and Coherency Enhanced Story Generation
• Changing the Mind of Transformers for Topically-Controllable Language Generation
• InFillmore: Frame-Guided Language Generation with Bidirectional Context