一种适用于专业搜索引擎的中文分词系统研究  

Research of Chinese word segmentation system applies in professional search engine

作　　者：王硕[1] 尤枫[1] 山岚[1] 赵恒永[1] 

机构地区：[1]北京化工大学信息科学与技术学院,北京100029

出　　处：《计算机工程与应用》2008年第19期142-145,共4页Computer Engineering and Applications

摘　　要：在对现有中文分词技术研究的基础上,提出了一种应用于化工专业领域的中文分词系统,先后介绍了首字哈希结合二分查找的词典机制,以及结合路径选择机制而改进了的层进式最短路径切词算法,并经过实验分析,在保证切分效率的同时,在一定程度上达到了消除歧义的效果。This article based on the research of current technology of Chinese word segmentation,proposes a Chinese word segmentation system to the chemical field,first introduces the dictionary mechanism combined first character hash indexing with binary search,then introduces an improved algorithm based on level-pattern shortest path method with the complementarity of the paths selection mechanism,at last,by analyzing the experiment＇s result,this system shows a desired effectiveness as well as eliminating the ambiguity to some extent.

关 键 词：中文分词 搜索引擎 首字哈希 层进式最短路径 路径选择 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]