Plan, Write, and Revise: an Interactive System for Open-Domain Story Generation
This addresses the problem of enhancing story quality and user engagement in AI-assisted writing for creative applications, though it is incremental in its approach to human-in-the-loop systems.
The authors tackled the challenge of open-domain story generation by developing a neural system that interacts with humans at various stages, resulting in a 10-50% improvement in story quality compared to less interactive baselines.
Story composition is a challenging problem for machines and even for humans. We present a neural narrative generation system that interacts with humans to generate stories. Our system has different levels of human interaction, which enables us to understand at what stage of story-writing human collaboration is most productive, both to improving story quality and human engagement in the writing process. We compare different varieties of interaction in story-writing, story-planning, and diversity controls under time constraints, and show that increased types of human collaboration at both planning and writing stages results in a 10-50% improvement in story quality as compared to less interactive baselines. We also show an accompanying increase in user engagement and satisfaction with stories as compared to our own less interactive systems and to previous turn-taking approaches to interaction. Finally, we find that humans tasked with collaboratively improving a particular characteristic of a story are in fact able to do so, which has implications for future uses of human-in-the-loop systems.