用数据挖掘技术进行中文地址解构的新方法  

A New Method to Extract Structure from Chinese Addresses Using Data Mining Technology

作　　者：李宝林[1] 王秀峰[1] 兰芸[2] 段菲[1] 

机构地区：[1]南开大学信息技术科学学院,天津300071 [2]北京航空航天大学高等教育研究所,北京100083

出　　处：《计算机工程与应用》2003年第13期72-74,87,共4页Computer Engineering and Applications

基　　金：天津21世纪青年科学基金资助(编号:003700111)

摘　　要：从数据挖掘的角度对中文地址解构规则的获取与应用进行研究。该文提出了一种高效自动获取地址解构规则的方法:首先利用文本挖掘技术从训练数据集中挖掘出候选规则,然后生成最终的强规则,同时构建地址元素特征词典。最后,根据获取的知识进行地址解析,提取文本地址组成元素。试验结果证实了该方法的可行性。This paper presents a novel data mining method to automatically elementize Chinese address seen as a plain text string into atomic structured elements like“Province”and“City”.Firstly,this way acquires a set of candidate rules from training data set and build them into strong rules.Secondly,it constructs the lexicon containing address element features.The rule set and the lexicon compose the knowledge base.Finally,the knowledge base can be used to extract structure from address in Chinese text.The experiment shows that a system using the method presented in this paper can work effectively.

关 键 词：文本地址 地址解构 数据挖掘 序贯规则 数字查找树 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]