Open-Domain Hierarchical Event Schema Induction by Incremental Prompting and Verification
This work addresses the challenge of generating complex event schemas for applications like story generation and knowledge representation, offering a more efficient and effective method compared to traditional information extraction approaches.
The paper tackled the problem of inducing open-domain hierarchical event schemas by proposing a new paradigm that treats schemas as commonsense knowledge derived from large language models, resulting in a 7.2% F1 improvement in temporal relations and 31.0% F1 improvement in hierarchical relations compared to direct LLM generation, and outperforming previous state-of-the-art models in human evaluations.
Event schemas are a form of world knowledge about the typical progression of events. Recent methods for event schema induction use information extraction systems to construct a large number of event graph instances from documents, and then learn to generalize the schema from such instances. In contrast, we propose to treat event schemas as a form of commonsense knowledge that can be derived from large language models (LLMs). This new paradigm greatly simplifies the schema induction process and allows us to handle both hierarchical relations and temporal relations between events in a straightforward way. Since event schemas have complex graph structures, we design an incremental prompting and verification method to break down the construction of a complex event graph into three stages: event skeleton construction, event expansion, and event-event relation verification. Compared to directly using LLMs to generate a linearized graph, our method can generate large and complex schemas with 7.2% F1 improvement in temporal relations and 31.0% F1 improvement in hierarchical relations. In addition, compared to the previous state-of-the-art closed-domain schema induction model, human assessors were able to cover $\sim$10% more events when translating the schemas into coherent stories and rated our schemas 1.3 points higher (on a 5-point scale) in terms of readability.