Lifelong Event Detection via Optimal Transport

Viet Dao, Van-Cuong Pham, Quyen Tran, Thanh-Thien Le, Linh Ngo, Thien Nguyen


Abstract
Continual Event Detection (CED) poses a formidable challenge due to the catastrophic forgetting phenomenon, where learning new tasks (with new coming event types) hampers performance on previous ones. In this paper, we introduce a novel approach, Lifelong Event Detection via Optimal Transport (**LEDOT**), that leverages optimal transport principles to align the optimization of our classification module with the intrinsic nature of each class, as defined by their pre-trained language modeling. Our method integrates replay sets, prototype latent representations, and an innovative Optimal Transport component. Extensive experiments on MAVEN and ACE datasets demonstrate LEDOT’s superior performance, consistently outperforming state-of-the-art baselines. The results underscore LEDOT as a pioneering solution in continual event detection, offering a more effective and nuanced approach to addressing catastrophic forgetting in evolving environments.
Anthology ID:
2024.emnlp-main.701
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12610–12621
Language:
URL:
https://aclanthology.org/2024.emnlp-main.701
DOI:
Bibkey:
Cite (ACL):
Viet Dao, Van-Cuong Pham, Quyen Tran, Thanh-Thien Le, Linh Ngo, and Thien Nguyen. 2024. Lifelong Event Detection via Optimal Transport. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 12610–12621, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Lifelong Event Detection via Optimal Transport (Dao et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.701.pdf
Software:
 2024.emnlp-main.701.software.zip