Lifelong Event Detection via Optimal Transport

TL;DR

This paper introduces LEDOT, a novel continual event detection method that uses optimal transport to mitigate catastrophic forgetting, achieving superior results on MAVEN and ACE datasets.

Contribution

LEDOT is the first to apply optimal transport principles to lifelong event detection, integrating replay, prototypes, and transport for improved performance.

Findings

LEDOT outperforms state-of-the-art baselines on MAVEN and ACE datasets.

Optimal transport effectively aligns class representations, reducing forgetting.

The approach offers a more nuanced understanding of evolving event types.

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.