Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection
This addresses the problem of event detection with limited labeled data for NLP applications, representing an incremental improvement over existing prototypical networks.
The paper tackles few-shot event detection by proposing a Dynamic-Memory-Based Prototypical Network (DMB-PN) that uses a Dynamic Memory Network to improve prototype learning and sentence encoding, resulting in better performance in handling sample scarcity and robustness with limited data.
Event detection (ED), a sub-task of event extraction, involves identifying triggers and categorizing event mentions. Existing methods primarily rely upon supervised learning and require large-scale labeled event datasets which are unfortunately not readily available in many real-life applications. In this paper, we consider and reformulate the ED task with limited labeled data as a Few-Shot Learning problem. We propose a Dynamic-Memory-Based Prototypical Network (DMB-PN), which exploits Dynamic Memory Network (DMN) to not only learn better prototypes for event types, but also produce more robust sentence encodings for event mentions. Differing from vanilla prototypical networks simply computing event prototypes by averaging, which only consume event mentions once, our model is more robust and is capable of distilling contextual information from event mentions for multiple times due to the multi-hop mechanism of DMNs. The experiments show that DMB-PN not only deals with sample scarcity better than a series of baseline models but also performs more robustly when the variety of event types is relatively large and the instance quantity is extremely small.