Plan-And-Write: Towards Better Automatic Storytelling

TL;DR

This paper introduces a hierarchical framework for open-domain automatic storytelling that improves story coherence and diversity by explicitly planning storylines before generation.

Contribution

It proposes a novel plan-and-write hierarchical approach with two planning strategies, advancing open-domain story generation beyond narrow or plot-restricted methods.

Findings

Stories with explicit planning are more coherent.

Planned stories are more diverse and on-topic.

Hierarchical planning improves automatic and human evaluation scores.

Abstract

Automatic storytelling is challenging since it requires generating long, coherent natural language to describes a sensible sequence of events. Despite considerable efforts on automatic story generation in the past, prior work either is restricted in plot planning, or can only generate stories in a narrow domain. In this paper, we explore open-domain story generation that writes stories given a title (topic) as input. We propose a plan-and-write hierarchical generation framework that first plans a storyline, and then generates a story based on the storyline. We compare two planning strategies. The dynamic schema interweaves story planning and its surface realization in text, while the static schema plans out the entire storyline before generating stories. Experiments show that with explicit storyline planning, the generated stories are more diverse, coherent, and on topic than those generated without creating a full plan, according to both automatic and human evaluations.