Continual Few-shot Event Detection via Hierarchical Augmentation Networks

Chenlong Zhang, Pengfei Cao, Yubo Chen, Kang Liu, Zhiqiang Zhang, Mengshu Sun, Jun Zhao


Abstract
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 Network (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.
Anthology ID:
2024.lrec-main.342
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
3868–3880
Language:
URL:
https://aclanthology.org/2024.lrec-main.342
DOI:
Bibkey:
Cite (ACL):
Chenlong Zhang, Pengfei Cao, Yubo Chen, Kang Liu, Zhiqiang Zhang, Mengshu Sun, and Jun Zhao. 2024. Continual Few-shot Event Detection via Hierarchical Augmentation Networks. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3868–3880, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Continual Few-shot Event Detection via Hierarchical Augmentation Networks (Zhang et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.lrec-main.342.pdf
Optional supplementary material:
 2024.lrec-main.342.OptionalSupplementaryMaterial.zip