Learning Prototype Representations Across Few-Shot Tasks for Event Detection

We address the sampling bias and outlier issues in few-shot learning for event detection, a subtask of information extraction. We propose to model the relations between training tasks in episodic few-shot learning by introducing cross-task prototypes. We further propose to enforce prediction consistency among classifiers across tasks to make the model more robust to outliers. Our extensive experiment shows a consistent improvement on three fewshot learning datasets. The findings suggest that our model is more robust when labeled data of novel event types is limited. The source code is available at http://github.com/laiviet/fsl-proact.