Human-in-the-Loop Schema Induction
Human-Computer Interaction
2023-08-23 v1 Computation and Language
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.
Cite
@article{arxiv.2302.13048,
title = {Human-in-the-Loop Schema Induction},
author = {Tianyi Zhang and Isaac Tham and Zhaoyi Hou and Jiaxuan Ren and Liyang Zhou and Hainiu Xu and Li Zhang and Lara J. Martin and Rotem Dror and Sha Li and Heng Ji and Martha Palmer and Susan Brown and Reece Suchocki and Chris Callison-Burch},
journal= {arXiv preprint arXiv:2302.13048},
year = {2023}
}
Comments
10 pages, ACL2023 demo track