analiza aiqbench
This paper introduces FSE, an architecture for continual named entity recognition that leverages a dual-expert system to balance knowledge retention with the ability to learn new entity types efficiently. By separating token-level filtering into a fast expert and classification into a slow task-specific expert, the model mitigates catastrophic forgetting while accelerating convergence on synthetic benchmarks like FewNERD. The approach represents a significant methodological advance in machine learning for natural language processing, specifically addressing stability-plasticity dilemmas without relying solely on large-scale data retraining.
FSE: Continual Learning for Named Entity Recognition by Fast-Slow Experts
arXiv:2607.22075v1 Announce Type: cross Abstract: 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.
Abstract: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.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2607.22075 [cs.CL]
(or arXiv:2607.22075v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2607.22075 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 236 cuvinte
Subiecte conexe
Game Design Creativity evals
LessWrong · 12 oct. 2026
Underwriting Superintelligence: Backing Agents you can Sue — Rune Kvist, AIUC
Latent Space · 16 sept. 2026
The J-Space Debate, Agent Swarms, and Pacing Frontier AI - Digital Minds Newsletter #4
LessWrong · 18 sept. 2026
J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses
LessWrong · 8 oct. 2026