Extending Event Detection to New Types with Learning from Keywords
This work addresses the problem of adapting event detection models to new event types for researchers and practitioners in natural language processing, representing an incremental improvement over traditional methods.
The paper tackles the limitation of predefined event types in event detection by proposing a novel formulation that describes types via keywords to match contexts, enabling adaptation to new types, and introduces a feature-based attention mechanism for convolutional neural networks, with extensive experiments demonstrating benefits for new type extension.
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.