Few-Shot Event Detection with Prototypical Amortized Conditional Random Field
Xin Cong, Shiyao Cui, Bowen Yu, Tingwen Liu, Wang Yubin, Bin Wang
Abstract
Event detection tends to struggle when it needs to recognize novel event types with a few samples. The previous work attempts to solve this problem in the identify-then-classify manner but ignores the trigger discrepancy between event types, thus suffering from the error propagation. In this paper, we present a novel unified model which converts the task to a few-shot tagging problem with a double-part tagging scheme. To this end, we first propose the Prototypical Amortized Conditional Random Field (PA-CRF) to model the label dependency in the few-shot scenario, which approximates the transition scores between labels based on the label prototypes. Then Gaussian distribution is introduced for modeling of the transition scores to alleviate the uncertain estimation resulting from insufficient data. Experimental results show that the unified models work better than existing identifythen-classify models and our PA-CRF further achieves the best results on the benchmark dataset FewEvent.