Continual Few-shot Event Detection via Hierarchical Augmentation Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911814337429504 |
|---|---|
| author | Zhang, Chenlong Cao, Pengfei Chen, Yubo Liu, Kang Zhang, Zhiqiang Sun, Mengshu Zhao, Jun |
| author_facet | Zhang, Chenlong Cao, Pengfei Chen, Yubo Liu, Kang Zhang, Zhiqiang Sun, Mengshu Zhao, Jun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_17733 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Continual Few-shot Event Detection via Hierarchical Augmentation Networks Zhang, Chenlong Cao, Pengfei Chen, Yubo Liu, Kang Zhang, Zhiqiang Sun, Mengshu Zhao, Jun Computation and Language 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. |
| title | Continual Few-shot Event Detection via Hierarchical Augmentation Networks |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2403.17733 |