CEO: Corpus-based Open-Domain Event Ontology Induction

TL;DR

CEO introduces a novel corpus-based method for inducing hierarchical open-domain event ontologies without direct supervision, improving coverage, accuracy, and interpretability over existing models.

Contribution

It is the first to induce hierarchical event ontologies with meaningful names across multiple open-domain corpora using a corpus-based, unsupervised approach.

Findings

Induces ontologies with better coverage and accuracy.

Successfully creates hierarchical schemas with meaningful labels.

Demonstrates effectiveness across eleven open-domain datasets.

Abstract

Existing event-centric NLP models often only apply to the pre-defined ontology, which significantly restricts their generalization capabilities. This paper presents CEO, a novel Corpus-based Event Ontology induction model to relax the restriction imposed by pre-defined event ontologies. Without direct supervision, CEO leverages distant supervision from available summary datasets to detect corpus-wise salient events and exploits external event knowledge to force events within a short distance to have close embeddings. Experiments on three popular event datasets show that the schema induced by CEO has better coverage and higher accuracy than previous methods. Moreover, CEO is the first event ontology induction model that can induce a hierarchical event ontology with meaningful names on eleven open-domain corpora, making the induced schema more trustworthy and easier to be further curated.