Zero-Shot On-the-Fly Event Schema Induction

TL;DR

This paper introduces a zero-shot, on-the-fly event schema induction method using large language models to generate comprehensive event schemas from minimal input, outperforming manual and supervised approaches in completeness and flexibility.

Contribution

The authors propose a novel zero-shot framework leveraging large language models for automatic event schema induction without manual data collection or predefined ontologies.

Findings

Generated schemas are more complete than human-curated ones in most scenarios.

The method performs comparably to supervised approaches that require real text data.

Schemas can be generated on any topic instantly without prior data collection.

Abstract

What are the events involved in a pandemic outbreak? What steps should be taken when planning a wedding? The answers to these questions can be found by collecting many documents on the complex event of interest, extracting relevant information, and analyzing it. We present a new approach in which large language models are utilized to generate source documents that allow predicting, given a high-level event definition, the specific events, arguments, and relations between them to construct a schema that describes the complex event in its entirety. Using our model, complete schemas on any topic can be generated on-the-fly without any manual data collection, i.e., in a zero-shot manner. Moreover, we develop efficient methods to extract pertinent information from texts and demonstrate in a series of experiments that these schemas are considered to be more complete than human-curated ones in the majority of examined scenarios. Finally, we show that this framework is comparable in performance with previous supervised schema induction methods that rely on collecting real texts while being more general and flexible without the need for a predefined ontology.