Viet Dao — accepted AI-conference papers

2024

Lifelong Event Detection via Optimal Transport

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

EMNLP 2024main

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 (**LED…

Cited by 2 Source ↗PDF ↗Scholar ↗

2024

SharpSeq: Empowering Continual Event Detection through Sharpness-Aware Sequential-task Learning

Thanh-Thien Le, Viet Dao, Linh Nguyen, Thi-Nhung Nguyen, Linh Ngo, Thien Nguyen

NAACL 2024long

Continual event detection is a cornerstone in uncovering valuable patterns in many dynamic practical applications, where novel events emerge daily. Existing state-of-the-art approaches with replay buffers still suffer from catastrophic forgetting, partially due to overly simplistic objective aggrega…

Cited by 8 Source ↗PDF ↗Scholar ↗