Lifelong Event Detection via Optimal Transport

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dao, Viet, Pham, Van-Cuong, Tran, Quyen, Le, Thanh-Thien, Van, Linh Ngo, Nguyen, Thien Huu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912069502107648
author Dao, Viet
Pham, Van-Cuong
Tran, Quyen
Le, Thanh-Thien
Van, Linh Ngo
Nguyen, Thien Huu
author_facet Dao, Viet
Pham, Van-Cuong
Tran, Quyen
Le, Thanh-Thien
Van, Linh Ngo
Nguyen, Thien Huu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_08905
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Lifelong Event Detection via Optimal Transport
Dao, Viet
Pham, Van-Cuong
Tran, Quyen
Le, Thanh-Thien
Van, Linh Ngo
Nguyen, Thien Huu
Computation and Language
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.
title Lifelong Event Detection via Optimal Transport
topic Computation and Language
url https://arxiv.org/abs/2410.08905