Human-in-the-loop Schema Induction
Human-in-the-loop Schema Induction
复制标题
DOI：
10.18653/v1/2023.acl-demo.1
复制
发表时间：
2023-02
期刊：
影响因子：
--
通讯作者：
Tianyi Zhang;Isaac Tham;Zhaoyi Hou;J. Ren;Liyang Zhou;Hainiu Xu;Li Zhang;Lara J. Martin;Rotem Dror;Sha Li;Heng Ji;Martha Palmer;S. Brown;Reece Suchocki;Chris Callison-Burch
中科院分区：
文献类型：
--
作者：
Tianyi Zhang;Isaac Tham;Zhaoyi Hou;J. Ren;Liyang Zhou;Hainiu Xu;Li Zhang;Lara J. Martin;Rotem Dror;Sha Li;Heng Ji;Martha Palmer;S. Brown;Reece Suchocki;Chris Callison-Burch
模式归纳构建了一个图形表示，解释事件如何在场景中展开。现有方法基于信息检索 (IR) 和信息提取 (IE)，通常人工管理有限。我们演示了由 GPT-3 支持的人机循环模式归纳系统。我们首先描述系统的不同模块，包括提示生成原理图元素、手动编辑这些元素以及将它们转换为模式图。通过对我们的系统与以前的系统进行定性比较，我们表明，我们的系统不仅比以前的方法更容易转移到新领域，而且由于我们的交互式界面，还减少了人工管理的工作。
Schema induction builds a graph representation explaining how events unfold in a scenario. Existing approaches have been based on information retrieval (IR) and information extraction (IE), often with limited human curation. We demonstrate a human-in-the-loop schema induction system powered by GPT-3. We first describe the different modules of our system, including prompting to generate schematic elements, manual edit of those elements, and conversion of those into a schema graph. By qualitatively comparing our system to previous ones, we show that our system not only transfers to new domains more easily than previous approaches, but also reduces efforts of human curation thanks to our interactive interface.