Continual Few-shot Event Detection via Hierarchical Augmentation Networks
This addresses a practical challenge for natural language processing applications where labeled data is scarce, though it appears incremental as it builds on existing continual and few-shot learning paradigms.
The paper tackles the problem of continual few-shot event detection, where models must learn new event types with limited labeled data while retaining knowledge of previous types, and demonstrates that their proposed Hierarchical Augmentation Networks significantly outperform state-of-the-art methods and ChatGPT in multiple tasks.
Traditional continual event detection relies on abundant labeled data for training, which is often impractical to obtain in real-world applications. In this paper, we introduce continual few-shot event detection (CFED), a more commonly encountered scenario when a substantial number of labeled samples are not accessible. The CFED task is challenging as it involves memorizing previous event types and learning new event types with few-shot samples. To mitigate these challenges, we propose a memory-based framework: Hierarchical Augmentation Networks (HANet). To memorize previous event types with limited memory, we incorporate prototypical augmentation into the memory set. For the issue of learning new event types in few-shot scenarios, we propose a contrastive augmentation module for token representations. Despite comparing with previous state-of-the-art methods, we also conduct comparisons with ChatGPT. Experiment results demonstrate that our method significantly outperforms all of these methods in multiple continual few-shot event detection tasks.