Decomposing Logits Distillation for Incremental Named Entity Recognition

Incremental Named Entity Recognition (INER) aims to continually train a model with new data, recognizing emerging entity types without forgetting previously learned ones. Prior INER methods have shown that Logits Distillation (LD), which involves preserving predicted logits via knowledge distillation, effectively alleviates this challenging issue. In this paper, we discover that a predicted logit can be decomposed into two terms that measure the likelihood of an input token belonging to a specific entity type or not. However, the traditional LD only preserves the sum of these two terms without considering the change in each component. To explicitly constrain each term, we propose a novel Decomposing Logits Distillation (DLD) method, enhancing the model's ability to retain old knowledge and mitigate catastrophic forgetting. Moreover, DLD is model-agnostic and easy to implement. Extensive experiments show that DLD consistently improves the performance of state-of-the-art INER methods across ten INER settings in three datasets.