Federated Incremental Named Entity Recognition

Zesheng Liu, Qiannan Zhu, Cuiping Li, Hong Chen


Abstract
Federated learning-based Named Entity Recognition (FNER) has attracted widespread attention through decentralized training on local clients. However, most FNER models assume that entity types are pre-fixed, so in practical applications, local clients constantly receive new entity types without enough storage to access old entity types, resulting in severe forgetting on previously learned knowledge. In addition, new clients collecting only new entity types may join the global training of FNER irregularly, further exacerbating catastrophic forgetting. To overcome the above challenges, we propose a Forgetting-Subdued Learning (FSL) model which solves the forgetting problem on old entity types from both intra-client and inter-client two aspects. Specifically, for intra-client aspect, we propose a prototype-guided adaptive pseudo labeling and a prototypical relation distillation loss to surmount catastrophic forgetting of old entity types with semantic shift. Furthermore, for inter-client aspect, we propose a task transfer detector. It can identify the arrival of new entity types that are protected by privacy and store the latest old global model for relation distillation. Qualitative experiments have shown that our model has made significant improvements compared to several baseline methods.
Anthology ID:
2025.coling-main.13
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
188–198
Language:
URL:
https://aclanthology.org/2025.coling-main.13/
DOI:
Bibkey:
Cite (ACL):
Zesheng Liu, Qiannan Zhu, Cuiping Li, and Hong Chen. 2025. Federated Incremental Named Entity Recognition. In Proceedings of the 31st International Conference on Computational Linguistics, pages 188–198, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Federated Incremental Named Entity Recognition (Liu et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.13.pdf