Wordcraft: a Human-AI Collaborative Editor for Story Writing
Andy Coenen, Luke Davis, Daphne Ippolito, Emily Reif, Ann Yuan

TL;DR
Wordcraft is a human-AI collaborative story writing tool that leverages conversational interfaces and few-shot learning to enhance creative writing with transformer-based language models.
Contribution
It introduces a novel interactive editor that supports diverse user-model interactions and explores human-in-the-loop training and evaluation methods.
Findings
Supports varied interaction modes for story writing
Facilitates probing of language model capabilities
Lays groundwork for future human-AI collaboration in creative tasks
Abstract
As neural language models grow in effectiveness, they are increasingly being applied in real-world settings. However these applications tend to be limited in the modes of interaction they support. In this extended abstract, we propose Wordcraft, an AI-assisted editor for story writing in which a writer and a dialog system collaborate to write a story. Our novel interface uses few-shot learning and the natural affordances of conversation to support a variety of interactions. Our editor provides a sandbox for writers to probe the boundaries of transformer-based language models and paves the way for future human-in-the-loop training pipelines and novel evaluation methods.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
[ML News] AI-generated patent approved | Germany gets an analog to OpenAI | ML cheats video games· youtube
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Multimodal Machine Learning Applications
