基于后缀数组的分词技术

Word Segment Based on Suffix Array

中文分词技术是机器翻译、分类、搜索引擎以及信息检索的基础,但是,互联网上不断出现的新词严重影响了分词的性能,为了提高新词的识别率,建立待分词内容的后缀数组,然后计算其公共前缀共同出现的次数,采用阈值对其进行过滤筛选出候选词语,实验结果表明,该方法在新词识别方面有一定的优势。

Chinese word segmentation technology is the basis of machine translation,classification,search engines,as well as information retrieval.But the Internet emerging new words have seriously affected the performance of word segmentation.To improve the recognition rate of new words,suffix array is used in this paper,and the number of length of common prefix is calculated.The candidates on their words are filtered out by the threshold.Experimental results show that the new word recognition method has advantages.