OntoED: Low-resource Event Detection with Ontology Embedding
This addresses data scarcity and generalization issues in event detection for natural language processing applications, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of event detection in low-resource scenarios by proposing OntoED, a framework that uses ontology embedding to leverage correlations among event types, resulting in improved performance, especially for data-scarce and unseen event types.
Event Detection (ED) aims to identify event trigger words from a given text and classify it into an event type. Most of current methods to ED rely heavily on training instances, and almost ignore the correlation of event types. Hence, they tend to suffer from data scarcity and fail to handle new unseen event types. To address these problems, we formulate ED as a process of event ontology population: linking event instances to pre-defined event types in event ontology, and propose a novel ED framework entitled OntoED with ontology embedding. We enrich event ontology with linkages among event types, and further induce more event-event correlations. Based on the event ontology, OntoED can leverage and propagate correlation knowledge, particularly from data-rich to data-poor event types. Furthermore, OntoED can be applied to new unseen event types, by establishing linkages to existing ones. Experiments indicate that OntoED is more predominant and robust than previous approaches to ED, especially in data-scarce scenarios.