融合机器阅读理解的中文医学命名实体识别方法  

Chinese Medical Named Entity Recognition Method Incorporating Machine Reading Comprehension

作　　者：罗媛媛 杨春明[1,3] 李波 张晖[2] 赵旭剑[1,3] LUO Yuanyuan;YANG Chunming;LI Bo;ZHANG Hui;ZHAO Xujian(School of Computer Science and Technology,Southwest University of Science and Technology,Mianyang,Sichuan 621000,China;School of Mathematics and Physics,Southwest University of Science and Technology,Mianyang,Sichuan 621000,China;Sichuan Big Data and Intelligent System Engineering Technology Research Center,Mianyang,Sichuan 621010,China)

机构地区：[1]西南科技大学计算机科学与技术学院,四川绵阳621000 [2]西南科技大学数理学院,四川绵阳621000 [3]四川省大数据与智能系统工程技术研究中心,四川绵阳621010

出　　处：《计算机科学》2023年第9期287-294,共8页Computer Science

基　　金：四川省科技厅重点研发项目(2021YFG0031);四川省省级科研院所科技成果转化项目(22YSZH0021)。

摘　　要：医学命名实体识别是自动构建大规模医学知识库的关键,但医学文本中存在实体嵌套现象,采用序列标注的方法不能识别出嵌套中的实体。文中提出了基于阅读理解框架的中文医学命名实体识别方法,该方法将嵌套命名实体识别问题建模为机器阅读理解问题,使用BERT建立阅读理解问题和医学文本之间的联系,并引入多头注意力机制强化问题和嵌套实体之间的语义联系,最后用两个分类器对实体开头和结尾位置进行预测。与目前5种主流方法相比,该方法取得了最优结果,综合F1值达到了67.65%;与经典的实体识别模型BiLSTM-CRF相比,F1值提升了7.17%,其中嵌套较多的临床表现实体提升16.81%。Medical named entity recognition is the key to automatically build a large-scale medical knowledge base.However,medical entities are often nested,and it can not be recognized by the sequence labeling method.This paper proposes a Chinese medical named entity recognition method based on reading comprehension framework.It models the nested named entity recognition problem as a machine reading problem,uses BERT to establish the connection between the reading comprehension problem and medical text,and introduces a multi-head attention mechanism to strengthen the semantic connection between the problem and nested named entity,and finally uses two classifiers to predict the beginning and end positions of entities.This method achieves the best results with an F1-score of 67.65%when compared with the current five mainstream methods.Compared with the most classical BiLSTM-CRF,the F1-score improves by 7.17%,and the nested“symptom”entities increase by 16.81%.

关 键 词：命名实体识别 中文医学 嵌套实体 机器阅读理解 多头注意力机制 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]