提出快慢专家机制，缓解命名实体识别持续学习中的遗忘问题。
FSE: Continual Learning for Named Entity Recognition by Fast-Slow Experts
- 快专家过滤不靠谱片段，慢专家专注分类，分工降低学习负担。
- 在OntoNotes和FewNERD上超越现有方法，收敛更快且抗遗忘能力更强。
- 适合需要持续学习新实体类型的场景，如动态知识库构建。
命名实体识别的持续学习（CLNER）使模型能增量学习新实体类型而不会遗忘旧知识。然而，现有方法存在灾难性遗忘和跨任务共享信息不足的问题。本文提出FSE，一种基于快慢专家的端到端跨度式NER模型。共享快专家学习词级关联，高效过滤不可能的候选片段；任务专属慢专家仅对剩余候选进行分类。该设计通过促进跨任务知识共享稳定学习，同时通过减少每轮学习负担保持模型可塑性。此外引入长度衰减负采样策略以缓解片段数量不平衡问题。在OntoNotes和FewNERD合成数据集上的大量实验表明，FSE在CLNER场景下达到当前最优性能，各组件有效性得到验证，兼具更快收敛速度与双专家协同功能。
原文摘要 · Abstract (English)
Continual Learning for Named Entity Recognition (CLNER) enable models to incrementally learn new entity types without forgetting previously acquired ones. However, existing methods suffer from catastrophic forgetting and insufficient exploitation of shared information across tasks. This paper proposes FSE, a Fast-Slow Experts enhanced span-based NER model for CLNER. The shared fast expert learns token-level links to efficiently filter out unlikely spans, while the task-specific slow expert performs span classification only on the remaining candidates. It stabilizes learning by promoting knowledge sharing across tasks and maintains plasticity by reducing learning burden at each task. A length-decay negative sampling strategy to mitigate span imbalance is also introduced. Extensive experiments on OntoNotes and FewNERD synthestic datasets demonstrate that FSE achieves state-of-the-art performance in CLNER scenarios, with effectiveness of each component, empirical evidence of faster convergence and expected functionality of both experts.
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。