摘要
随着医学人工智能的发展,医疗领域的知识抽取成为研究热点,其中诊疗关系的自动识别和抽取有助于医生进行诊疗决策。为了提高关系抽取的效果,提出一种结合规则聚类和词频分析的方法。从医疗文本中自动抽取关系发现词作为额外特征输入,并融合深度学习模型进行医疗领域关系抽取。使用以疾病为中心的诊疗流程相关文本展开实验验证,结果表明,将该方法用于医疗关系抽取可以显著提升效果。
With the development of medical artificial intelligence,knowledge extraction in the medical field has become a research hotspot.The automatic identification and extraction of diagnosis and treatment relationship can help doctors in decision making.In order to improve the effect on the relation extraction,this paper proposes a method combining rule clustering and word frequency analysis.It automatically extracted relation discovery words from medical text as the additional feature input,and integrated the deep learning model to extract relations in the medical field.This paper uses the texts related to the disease-centered diagnosis and treatment process to carry out experiments to verify the effectiveness of the method.The results show that the method for medical relationship extraction can significantly improve the effect.
作者
高峰
杨佳欣
顾进广
Gao Feng;Yang Jiaxin;Gu Jinguang(School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,Hubei,China;Big Data Science and Engineering Research Institute,Wuhan University of Science and Technology,Wuhan 430065,Hubei,China;Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial,Wuhan 430065,Hubei,China)
出处
《计算机应用与软件》
北大核心
2021年第12期168-173,共6页
Computer Applications and Software
基金
国家自然科学基金项目(U1836118,61673304)
国家社科基金重大计划项目(11&ZD189)
湖北省自然科学基金项目(2018CFB194)。
关键词
人工智能
医疗领域
关系抽取
深度学习
关系发现词
Artificial intelligence
Medical field
Relation extraction
Deep learning
Relation discovery words
