Efficient Zero-shot Event Extraction with Context-Definition Alignment

TL;DR

This paper introduces ZED, a zero-shot event extraction model that uses transformer-based semantic alignment of event definitions and mentions, significantly improving performance and speed over previous methods.

Contribution

The paper proposes a novel zero-shot event extraction approach using definition semantics and contrastive learning, enhancing generalization to unseen event types.

Findings

ZED outperforms previous zero-shot EE methods on MAVEN dataset.

ZED achieves faster inference speed due to disjoint design.

ZED also improves few-shot event extraction performance.

Abstract

Event extraction (EE) is the task of identifying interested event mentions from text. Conventional efforts mainly focus on the supervised setting. However, these supervised models cannot generalize to event types out of the pre-defined ontology. To fill this gap, many efforts have been devoted to the zero-shot EE problem. This paper follows the trend of modeling event-type semantics but moves one step further. We argue that using the static embedding of the event type name might not be enough because a single word could be ambiguous, and we need a sentence to define the type semantics accurately. To model the definition semantics, we use two separate transformer models to project the contextualized event mentions and corresponding definitions into the same embedding space and then minimize their embedding distance via contrastive learning. On top of that, we also propose a warming phase to help the model learn the minor difference between similar definitions. We name our approach Zero-shot Event extraction with Definition (ZED). Experiments on the MAVEN dataset show that our model significantly outperforms all previous zero-shot EE methods with fast inference speed due to the disjoint design. Further experiments also show that ZED can be easily applied to the few-shot setting when the annotation is available and consistently outperforms baseline supervised methods.