Lifelong Event Detection via Optimal Transport
This addresses the problem of forgetting old event types when learning new ones in NLP applications, representing a novel method for a known bottleneck.
The paper tackles catastrophic forgetting in continual event detection by introducing LEDOT, which uses optimal transport to align class-specific optimization with pre-trained language models, achieving superior performance on MAVEN and ACE datasets compared to state-of-the-art baselines.
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.