Hierarchical Neural Story Generation
This work addresses the problem of generating coherent and fluent stories for creative writing applications, representing an incremental improvement over existing methods.
The paper tackled story generation by introducing a hierarchical approach that first generates a premise and then expands it into text, achieving a two-to-one preference over strong baselines in human evaluations.
We explore story generation: creative systems that can build coherent and fluent passages of text about a topic. We collect a large dataset of 300K human-written stories paired with writing prompts from an online forum. Our dataset enables hierarchical story generation, where the model first generates a premise, and then transforms it into a passage of text. We gain further improvements with a novel form of model fusion that improves the relevance of the story to the prompt, and adding a new gated multi-scale self-attention mechanism to model long-range context. Experiments show large improvements over strong baselines on both automated and human evaluations. Human judges prefer stories generated by our approach to those from a strong non-hierarchical model by a factor of two to one.