Corpus-based Open-Domain Event Type Induction

TL;DR

This paper introduces a novel corpus-based method for automatically inducing open-domain event types by clustering predicate-object pairs, eliminating the need for predefined types and annotations.

Contribution

It proposes a new approach that represents event types as clusters of predicate sense and object head pairs, using joint embedding and clustering techniques.

Findings

Successfully discovers salient event types across multiple datasets

Achieves high-quality event type induction validated by automatic and human evaluations

Operates effectively without predefined event types or annotations

Abstract

Traditional event extraction methods require predefined event types and their corresponding annotations to learn event extractors. These prerequisites are often hard to be satisfied in real-world applications. This work presents a corpus-based open-domain event type induction method that automatically discovers a set of event types from a given corpus. As events of the same type could be expressed in multiple ways, we propose to represent each event type as a cluster of <predicate sense, object head> pairs. Specifically, our method (1) selects salient predicates and object heads, (2) disambiguates predicate senses using only a verb sense dictionary, and (3) obtains event types by jointly embedding and clustering <predicate sense, object head> pairs in a latent spherical space. Our experiments, on three datasets from different domains, show our method can discover salient and high-quality event types, according to both automatic and human evaluations.