Chinese Medical Entity Recognition Model Based on Character and Word Vector Fusion

Abstract

The medical information carried in electronic medical records has high clinical research value, and medical named entity recognition is the key to extracting valuable information from large-scale medical texts. At present, most of the studies on Chinese medical named entity recognition are based on character vector model or word vector model. Owing to the complexity and specificity of Chinese text, the existing methods may fail to achieve good performance. In this study, we propose a Chinese medical named entity recognition method that fuses character and word vectors. The method expresses Chinese texts as character vectors and word vectors separately and fuses them in the model for features. The proposed model can effectively avoid the problems of missing character vector information and inaccurate word vector partitioning. On the CCKS 2019 dataset for the named entity recognition task of Chinese electronic medical records, the proposed model achieves good performance and can effectively improve the accuracy of Chinese medical named entity recognition compared with other baseline models.

Chinese medical named entity recognition of long text based on deep learning

“…Experimental results have demonstrated that the model, which fuses character and word information, exhibits stronger entity recognition capabilities. Zhang et al [17] proposed a method that represents Chinese text as both character vectors and word vectors, which are integrated into a feature model. This model effectively addresses the issues of missing information in character vectors and inaccurate division in word vectors.…”

Surgical procedure long terms recognition from Chinese literature incorporating structural feature

“…The dictionary-based approaches face pretty much the same problem in covering all related entities, which causes poor recognition performance [ 31 ]. Machine learning-based approach at earlier stage takes a naïve resolution by simply classifying each word independently [ 32 ]. The main problem with this resolution is it assumes that named entity labels are independent which is not the case.…”