The Art of Prompting: Event Detection based on Type Specific Prompts
This improves event detection for NLP applications, especially in low-data scenarios, but is incremental as it builds on existing prompting methods.
The paper tackles event detection by comparing prompts for event types and developing a unified framework for supervised, few-shot, and zero-shot settings, resulting in up to 24.3% F-score gain over previous state-of-the-art baselines.
We compare various forms of prompts to represent event types and develop a unified framework to incorporate the event type specific prompts for supervised, few-shot, and zero-shot event detection. The experimental results demonstrate that a well-defined and comprehensive event type prompt can significantly improve the performance of event detection, especially when the annotated data is scarce (few-shot event detection) or not available (zero-shot event detection). By leveraging the semantics of event types, our unified framework shows up to 24.3\% F-score gain over the previous state-of-the-art baselines.