A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation
This addresses the challenge of semantic coherence in narrative story generation, which is incremental as it builds on existing generative models.
The paper tackles the problem of generating coherent narrative stories by proposing a skeleton-based model that first generates critical phrases and then expands them into sentences, resulting in a 20.1% improvement in G-score in human evaluation.
Narrative story generation is a challenging problem because it demands the generated sentences with tight semantic connections, which has not been well studied by most existing generative models. To address this problem, we propose a skeleton-based model to promote the coherence of generated stories. Different from traditional models that generate a complete sentence at a stroke, the proposed model first generates the most critical phrases, called skeleton, and then expands the skeleton to a complete and fluent sentence. The skeleton is not manually defined, but learned by a reinforcement learning method. Compared to the state-of-the-art models, our skeleton-based model can generate significantly more coherent text according to human evaluation and automatic evaluation. The G-score is improved by 20.1% in the human evaluation. The code is available at https://github.com/lancopku/Skeleton-Based-Generation-Model