Semantically-informed Hierarchical Event Modeling

TL;DR

This paper introduces a novel semi-supervised hierarchical event modeling framework that integrates ontological knowledge at multiple levels, improving event representation and outperforming previous models across various datasets and metrics.

Contribution

The work presents a doubly hierarchical, semi-supervised event model that incorporates partial semantic ontological knowledge at multiple abstraction levels, enhancing event modeling capabilities.

Findings

Outperforms previous state-of-the-art by up to 8.5%

Effective integration of structured ontological knowledge improves event representations

Model demonstrates robustness across different datasets and evaluation metrics

Abstract

Prior work has shown that coupling sequential latent variable models with semantic ontological knowledge can improve the representational capabilities of event modeling approaches. In this work, we present a novel, doubly hierarchical, semi-supervised event modeling framework that provides structural hierarchy while also accounting for ontological hierarchy. Our approach consists of multiple layers of structured latent variables, where each successive layer compresses and abstracts the previous layers. We guide this compression through the injection of structured ontological knowledge that is defined at the type level of events: importantly, our model allows for partial injection of semantic knowledge and it does not depend on observing instances at any particular level of the semantic ontology. Across two different datasets and four different evaluation metrics, we demonstrate that our approach is able to out-perform the previous state-of-the-art approaches by up to 8.5%, demonstrating the benefits of structured and semantic hierarchical knowledge for event modeling.