GenCNER: A Generative Framework for Continual Named Entity Recognition
This addresses the challenge of continually learning new entity types in NER for real-world applications, representing an incremental improvement over existing continual learning methods.
The paper tackles the problem of catastrophic forgetting and semantic shift in continual named entity recognition (CNER) by proposing GenCNER, a generative framework that converts CNER into entity triplet sequence generation and uses pseudo labeling with knowledge distillation. It outperforms previous state-of-the-art methods on benchmark datasets, achieving the smallest gap compared to non-continual learning results.
Traditional named entity recognition (NER) aims to identify text mentions into pre-defined entity types. Continual Named Entity Recognition (CNER) is introduced since entity categories are continuously increasing in various real-world scenarios. However, existing continual learning (CL) methods for NER face challenges of catastrophic forgetting and semantic shift of non-entity type. In this paper, we propose GenCNER, a simple but effective Generative framework for CNER to mitigate the above drawbacks. Specifically, we skillfully convert the CNER task into sustained entity triplet sequence generation problem and utilize a powerful pre-trained seq2seq model to solve it. Additionally, we design a type-specific confidence-based pseudo labeling strategy along with knowledge distillation (KD) to preserve learned knowledge and alleviate the impact of label noise at the triplet level. Experimental results on two benchmark datasets show that our framework outperforms previous state-of-the-art methods in multiple CNER settings, and achieves the smallest gap compared with non-CL results.