Narrative Interpolation for Generating and Understanding Stories

TL;DR

This paper introduces a narrative interpolation method using GPT-2 that enables controlled story generation guided by user-specified endings, improving coherence and reducing manual effort.

Contribution

The authors develop an interpolation-based narrative generation technique with a reranker for coherence, allowing guided story creation with specified endings.

Findings

Generated narratives are coherent and faithful to endings.

The method reduces manual effort compared to previous approaches.

Human evaluation confirms improved story quality.

Abstract

We propose a method for controlled narrative/story generation where we are able to guide the model to produce coherent narratives with user-specified target endings by interpolation: for example, we are told that Jim went hiking and at the end Jim needed to be rescued, and we want the model to incrementally generate steps along the way. The core of our method is an interpolation model based on GPT-2 which conditions on a previous sentence and a next sentence in a narrative and fills in the gap. Additionally, a reranker helps control for coherence of the generated text. With human evaluation, we show that ending-guided generation results in narratives which are coherent, faithful to the given ending guide, and require less manual effort on the part of the human guide writer than past approaches.