Phenonizer: A Fine-Grained Phenotypic Named Entity Recognizer for Chinese Clinical Texts

Figure 4

The overall framework of Phenonizer. Because of BERT, the special symbol [CLS] needs to be added before every sentence for classification output. represents the input embedding, which is the sum of token embedding, segmentation embedding, and position embedding. represents the contextual representation of token and will be used as the input of BiLSTM. are decoded by the CRF layer to get the optimal annotation sequences.