期刊论文

中文

情报工程

2095-915X

2023

9

05

112-122

10.3772/j.issn.2095-915x.2023.05.009

21YJC870002:教育部人文社会科学研究项目 2022010801020287:武汉市知识创新专项项目 :富媒体数字出版内容组织与知识服务重点实验室开放基金项目

本校为第一机构

[目的/意义]为进一步提升中医药古文献命名实体识别的准确性,以信息化手段辅助现代中医学者进行医学诊断与临床决策,促进中医学的传承与创新.[方法/过程]提出一种集成字符与词汇信息的中医药古文献命名实体识别的Lattice LSTM模型,对《伤寒论》的疾病、证候、方剂、症状和药材五类实体进行抽取;在抽取出的实体基础上,人工提取实体间关系,利用Neo4j搭建了中医药知识图谱;最后以新冠肺炎为例,在图谱上完成相关检索.[结果/结论]实验结果表明,Lattice LSTM在中医术语识别上性能最优,F1值达到95.66%,比主流模型BiLSTM-CRF提升了1.68%,可用于中医药古文献的实体识别;搭建的中医药知识图谱也验证了主模...

[Objective/Significance]In order to further improve the accuracy of named entity recognition in ancient Chinese medicine literatures,using information tools to assist modern Chinese medicine practitioners in medical diagnosis and clinical decision-making,promote the inheritance and innovation of traditional Chinese medicine.[Methods/Processes]This paper proposes a named entity recognition model of ancient Chinese medicine literatures called Lattice LSTM model that integrates character information and lexical information to extract five entities:disease,syndrome,prescription,symptom and medicin...