Wordcraft: a Human-AI Collaborative Editor for Story Writing
Andy Coenen Luke Davis Daphne Ippolito Emily Reif Ann Yuan Google Research
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.
中文速览
真实写作场景中的语言模型往往只能做"续写"这一件事，Wordcraft 想打破这个局限，让作家和 AI 像聊天一样协作完成故事的规划、写作与修改。系统的核心思路是用少样本学习（few-shot learning）把对话模型 Meena 改造成多面手助手——在输入里塞几个示范例子，就能让同一个模型完成续写、填空、扩写、改写等多种任务，而无需为每项功能单独训练一个模型。初步实验表明，对话模型比同等规模的通用语言模型更适合这类交互，因为它在困惑时会直接说"我不明白"，而不是生成一段驴唇不对马嘴的文字；不过模型输出质量仍然参差不齐，提示语措辞稍有变化就会引发较大波动。这项工作的意义在于它既是一个探索人机协作写作边界的实验平台，也为后续收集真实用户反馈、构建人在回路（human-in-the-loop）训练流程奠定了基础。
原文 arXiv:2107.07430;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2107.07430v1