基于BERT-BiLSTM-CRF的中医医案命名实体识别方法

Named entity recognition of TCM medical records based on BERT-BiLSTM-CRF

中医医案蕴含着丰富的中医经验知识,研究如何有效的从中医医案文本中挖掘有用实体信息具有重要意义。基于中国现代名医医案数据集,提出一种基于BERT-BiLSTM-CRF模型的中医医案命名实体识别方法。首先使用BERT语言模型进行文本特征提取,然后通过BiLSTM算法来获取上下文的信息,最后通过CRF算法来获取全局最优解并最终输出中医医案命名实体结果。实验表明,该方法相比于以往的中医医案命名实体方法的准确率、召回率、F1值有明显提升。

TCM medical records contain rich TCM experience and knowledge. It has great significance to study how to effectively mine useful entity information from TCM medical records. Based on the data set of modern famous Chinese medical records, a named entity recognition method of TCM medical records based on BERT-BiLSTM-CRF model is proposed. First, the BERT language model is used to extract text features, then the BiLSTM algorithm is used to obtain context information, and finally the CRF algorithm is used to obtain the global optimal solution, and the TCM medical case named entity result is output. Experiments show that the accuracy, recall and F1 value of this method are significantly improved compared with the previous TCM case named entity method.