Human-in-the-Loop Schema Induction
This work addresses schema induction for scenarios, offering a more efficient and adaptable solution for domains requiring event graph representations, though it appears incremental as it builds on existing methods with human interaction.
The paper tackles the problem of schema induction for event graphs by introducing a human-in-the-loop system powered by GPT-3, which reduces human curation effort and improves transfer to new domains compared to previous IR- and IE-based approaches.
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.