用最优传输缓解事件检测中的遗忘问题
Lifelong Event Detection via Optimal Transport
- 基于语言模型构建类原型，通过最优传输对齐分类优化
- 在MAVEN和ACE数据集上超越现有最佳方法
- 适合持续学习场景下的事件检测任务
持续事件检测（CED）因灾难性遗忘现象面临巨大挑战，即学习新任务（新事件类型）会损害对旧任务的性能。本文提出一种新方法——基于最优传输的终身事件检测（LEDOT），利用最优传输原理将分类模块的优化与预训练语言模型定义的每类内在特性对齐。该方法融合回放集、原型潜在表示及创新的最优传输组件。在MAVEN和ACE数据集上的大量实验表明，LEDOT性能显著优于现有先进基线。结果证实LEDOT是持续事件检测领域的开创性解决方案，为应对动态环境中的灾难性遗忘提供了更有效、更精细的方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。