摘要
从系统架构、语料库构建、应用效果3方面阐述临床文本自然语言处理系统cTAKES构建方法,从设计基于开源框架的系统架构、开发模块化组件、构建临床语料库、注重创新以及针对中文特点建设系统5个方面提出对我国中文临床文本自然语言处理系统构建的建议。
The paper elaborates on the method for building cTAKES, a clinical text natural language processing system, from the three aspects of system architecture, building of corpus and application effect, and puts forward recommendations on the building of Chinese clinical text natural language processing system from the five aspects, including design of system architecture based on open source framework, development of modular components, building of clinical corpus, attention given to innovation and building of the system in the light of the feature of Chinese language.
作者
杨晨柳
胡佳慧
方安
王蕾
任慧玲
YANG Chenliu;HU Jiahui;FANG An;WANG Lei;REN Huiling(Institute of Medical Information, Chinese Academy of Medical Sciences, Beijing 100020, China)
出处
《医学信息学杂志》
CAS
2018年第12期48-53,共6页
Journal of Medical Informatics
基金
中国医学科学院医学与健康科技创新工程项目(项目编号:2017-I2M-3-014)
中国医学科学院中央级公益性科研院所基本科研业务费项目(项目编号:2018PT33005)