Hierarchical Event Grounding

TL;DR

This paper introduces a hierarchical event grounding task linking text mentions to multi-level event structures in a knowledge base, utilizing a hierarchical loss to improve retrieval and enable discovery of unseen event hierarchies.

Contribution

It extends event grounding to hierarchical structures, proposing a retrieval method with a hierarchical loss and demonstrating its effectiveness on multilingual datasets.

Findings

Hierarchical loss improves retrieval accuracy.

Method effectively links mentions to hierarchical event structures.

System aids in discovering unseen event hierarchies.

Abstract

Event grounding aims at linking mention references in text corpora to events from a knowledge base (KB). Previous work on this task focused primarily on linking to a single KB event, thereby overlooking the hierarchical aspects of events. Events in documents are typically described at various levels of spatio-temporal granularity (Glavas et al. 2014). These hierarchical relations are utilized in downstream tasks of narrative understanding and schema construction. In this work, we present an extension to the event grounding task that requires tackling hierarchical event structures from the KB. Our proposed task involves linking a mention reference to a set of event labels from a subevent hierarchy in the KB. We propose a retrieval methodology that leverages event hierarchy through an auxiliary hierarchical loss (Murty et al. 2018). On an automatically created multilingual dataset from Wikipedia and Wikidata, our experiments demonstrate the effectiveness of the hierarchical loss against retrieve and re-rank baselines (Wu et al. 2020; Pratapa, Gupta, and Mitamura 2022). Furthermore, we demonstrate the systems' ability to aid hierarchical discovery among unseen events.