CEO: Corpus-based Open-Domain Event Ontology Induction
This addresses the generalization problem in event-centric NLP models for researchers and practitioners, offering a novel approach to ontology induction.
The paper tackles the limitation of pre-defined event ontologies in NLP by introducing CEO, a corpus-based model that induces open-domain event ontologies without direct supervision, achieving better coverage and accuracy than previous methods on three datasets and enabling hierarchical induction on eleven corpora.
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.