Chinese Medical Named Entity Recognition(CMNER)focuses on extracting entities from unstructured Chinese medical texts.Current character-based CMNER models inadequately address the distinct features of Chinese characters from various angles,thereby limiting their efficacy in CMNER applications.To address this,a model leveraging multigranular glyph information enhancement for Chinese medical named entity recognition is introduced.This model integrates the glyph spatial structure and radical representation of Chinese characters,aligning them with domain-specific lexicon-based word information.This approach enriches the semantic and boundary potential of characters.Through a gating mechanism,the model effectively combines domain-specific terms with the multifaceted glyph features of Chinese characters,ensuring comprehensive consideration of both domain relevance and intrinsic character details,thereby enhancing its capacity for medical entity recognition.The model employs multigranular glyph-enhanced character representations in the Bidirectional Long Short-Term Memory(BiLSTM)and Conditional Random Field(CRF)layers for contextual encoding and label decoding,respectively.Experimental results demonstrate that the proposed model surpasses the best baseline model,achieving an increase in F1 scores of 1.04% and 0.62% on the IMCS21 and CMeEE datasets,respectively.Ablation studies further confirm the efficacy of each component,highlighting the model's superiority in recognizing Chinese medical named entities.
named entity recognitionmedical domainglyph structuregating mechanismdomain lexicon
国家科技期刊平台
NSTL
维普
万方数据
