Research on Named Entity Recognition Technology based on pre-trained model
Qingfeng Hu · 2022 2nd International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI) · 2022
The pretraining model has the problems of large number of parameters, complex structure, and difficult to be compressed into a small model with both performance in practical deployment. Aiming at the above problems, this paper proposes a lightweight entity recognition model with good performance by using the framework of knowledge distillation to supervise and guide the student entity recognition model through the teacher entity recognition model. Finally, the feasibility and effectiveness of the method proposed in this chapter are verified by experiments.