Medical Name Entity Recognition Based on Lexical Enhancement and Global Pointer

Named entity recognition (NER) in biological sources, also called medical named (MNER), attempts to identify and categorize terminology electronic records. Deep neural networks have recently demonstrated substantial effectiveness MNER. However, Chinese MNER has issues that cannot use lexical information involve nested entities. To address these problems, we propose a model which can handle both non-nested The uses simple enhancement method for merging into each character's vector representation, then the Global Pointer approach recognition. Furthermore, retrain pre-trained with corpus incorporate knowledge, resulting F1 score of 68.13% on dataset CMeEE, 95.56% CCKS2017, 85.89% CCKS2019, 92.08% CCKS2020. These data demonstrate efficacy our proposed model.