摘要
为提高姓名识别的准确性并加快识别的速度,受生物免疫系统自学习、免疫记忆等特征启发,基于人工免疫原理,提出了一种新的中文姓名识别模型。给出了自体/非自体、抗体/抗原的定义,建立了免疫学习、免疫识别和免疫记忆机制。对模型进行了仿真,并完成了验证实验。实验结果表明该方法较传统的基于统计、基于语料库和结合决策树的姓名识别方法更有效,为文本挖掘提供了一种较好的解决方案。
In order to improve the precision and increase the speed of Chinese personal name recognition,a new model hased on artificial immune system for Chinese personal name recognition was proposed.The concepte of “self”,“nonself”,“antibody”and“antigen”were defined.The mechanisms of immune leaming,immune recognition and immurne memory were built,The correlative algorithm was preaented,The results showed that the novel method is more effective in some aspects than the traditional ones based on statistics,corpus,and decision tree,thus,it provides a good solution to the field of text mining.
出处
《四川大学学报（工程科学版）》
EI
CAS
CSCD
北大核心
2006年第1期98-102,共5页
Journal of Sichuan University (Engineering Science Edition)
基金
国家自然科学基金(6037311060573130)
教育部博士点基金(20030610003)
教育部新世纪优秀人才计划(NCET-04-0870)
四川大学科技创新基金资助项目(2004CF10)
关键词
人工免疫
文本挖掘
姓名识别
artificial immune
text mining
name recognition
