基于重现的无词典分词方法在中文生物医学文本挖掘中的应用  

The Applications of a Method for Chinese Word Segmentation without Thesaurus Based on Recurrence in the Text Mining of Chinese Biomedical Literature

作　　者：王军辉[1] 胡铁军[1] 李丹亚[1] 

机构地区：[1]中国医学科学院医学信息研究所,北京100020

出　　处：《医学信息学杂志》2009年第2期21-25,共5页Journal of Medical Informatics

摘　　要：在对文本挖掘和中文分词方法进行概述的基础上,结合中文生物医学文本的特点,提出基于重现的无词典分词方法在构建医学文献相关性数据库、发现医学新名词、预测新兴研究趋势和基于文献的知识发现中的应用设想。Based on a brief introduction of the principle of text mining and the methods of Chinese word segmentation, combined with the characteristics of Chinese biomedical text, the paper puts forward application assumptions of Chinese word segmentation without thesaurus method based on recurrence in constructing medical related articles databases, screening new medical terms, detecting research trend and knowledge discovery based on literatures.

关 键 词：无词典分词 数据挖掘 文本挖掘 知识发现 文献相关性数据库 

分 类 号：R-5[医药卫生]