Identity and Granularity of Events in Text

TL;DR

This paper presents a method for detecting and modeling events in news articles using RDF, addressing cross-document coreference by defining event identity and granularity, and analyzing their interconnections.

Contribution

It introduces a component-based approach to event semantics that models event identity and granularity, outperforming similar methods under certain conditions.

Findings

Performs close to state-of-the-art in cross-document event coreference.

Outperforms other methods with comparable event detection quality.

Highlights the link between event granularity and identity.

Abstract

In this paper we describe a method to detect event descrip- tions in different news articles and to model the semantics of events and their components using RDF representations. We compare these descriptions to solve a cross-document event coreference task. Our com- ponent approach to event semantics defines identity and granularity of events at different levels. It performs close to state-of-the-art approaches on the cross-document event coreference task, while outperforming other works when assuming similar quality of event detection. We demonstrate how granularity and identity are interconnected and we discuss how se- mantic anomaly could be used to define differences between coreference, subevent and topical relations.