# Human-in-the-Loop Schema Induction

## TL;DR

This paper presents a human-in-the-loop schema induction system utilizing GPT-3, which simplifies schema creation, enhances domain transferability, and reduces human curation effort through an interactive interface.

## Contribution

The paper introduces a novel human-in-the-loop schema induction system powered by GPT-3, combining automated generation with manual editing for improved efficiency.

## Key findings

- System transfers to new domains more easily than previous approaches.
- Reduces human curation effort via an interactive interface.
- Qualitative comparison shows improved performance over prior methods.

## 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.