Human-in-the-Loop Schema Induction
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

Abstract
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.
View on arXivComments on this paper