Learning to Predict Explainable Plots for Neural Story Generation
This work addresses the problem of interpretability in story generation for NLP applications, offering a method to make generated stories more coherent and explainable.
The paper tackles the challenge of generating explainable high-level plots in neural story generation by proposing a latent variable model that uses natural language outlines as latent variables, achieving significant improvements over state-of-the-art methods in automatic and human evaluations.
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.