Cue Me In: Content-Inducing Approaches to Interactive Story Generation

TL;DR

This paper introduces interactive story generation methods that incorporate user-provided cue phrases during the process, resulting in more coherent and personalized stories compared to traditional one-shot approaches.

Contribution

It proposes two novel content-inducing techniques for interactive story generation that effectively utilize mid-level user cues to improve story coherence and personalization.

Findings

Generated stories are more topically coherent.

User-guided stories are more personalized.

Methods outperform baseline models in evaluations.

Abstract

Automatically generating stories is a challenging problem that requires producing causally related and logical sequences of events about a topic. Previous approaches in this domain have focused largely on one-shot generation, where a language model outputs a complete story based on limited initial input from a user. Here, we instead focus on the task of interactive story generation, where the user provides the model mid-level sentence abstractions in the form of cue phrases during the generation process. This provides an interface for human users to guide the story generation. We present two content-inducing approaches to effectively incorporate this additional information. Experimental results from both automatic and human evaluations show that these methods produce more topically coherent and personalized stories compared to baseline methods.