Few-shot Event Detection: An Empirical Study and a Unified View
This work addresses the lack of standardization in few-shot event detection for researchers, offering incremental improvements through a unified view and better baseline.
The paper tackles the discrepancies in few-shot event detection by conducting an empirical study and proposing a unified framework, resulting in a new baseline that outperforms existing methods by up to 2.7% F1 score in low-resource settings.
Few-shot event detection (ED) has been widely studied, while this brings noticeable discrepancies, e.g., various motivations, tasks, and experimental settings, that hinder the understanding of models for future progress.This paper presents a thorough empirical study, a unified view of ED models, and a better unified baseline. For fair evaluation, we compare 12 representative methods on three datasets, which are roughly grouped into prompt-based and prototype-based models for detailed analysis. Experiments consistently demonstrate that prompt-based methods, including ChatGPT, still significantly trail prototype-based methods in terms of overall performance. To investigate their superior performance, we break down their design elements along several dimensions and build a unified framework on prototype-based methods. Under such unified view, each prototype-method can be viewed a combination of different modules from these design elements. We further combine all advantageous modules and propose a simple yet effective baseline, which outperforms existing methods by a large margin (e.g., 2.7% F1 gains under low-resource setting).