Extending Event Detection to New Types with Learning from Keywords

TL;DR

This paper proposes a new keyword-based approach for event detection that allows models to adapt to new event types and introduces a novel attention mechanism for improved performance.

Contribution

It introduces a keyword-based formulation for event detection and a novel feature-based attention mechanism for CNNs, enabling better adaptation to new event types.

Findings

Enhanced ability to detect new event types

Improved performance with the attention mechanism

Effective in diverse document contexts

Abstract

Traditional event detection classifies a word or a phrase in a given sentence for a set of predefined event types. The limitation of such predefined set is that it prevents the adaptation of the event detection models to new event types. We study a novel formulation of event detection that describes types via several keywords to match the contexts in documents. This facilitates the operation of the models to new types. We introduce a novel feature-based attention mechanism for convolutional neural networks for event detection in the new formulation. Our extensive experiments demonstrate the benefits of the new formulation for new type extension for event detection as well as the proposed attention mechanism for this problem.