快速书面汉语自动分词系统及其算法设计
A Fast Automatic Word Segmentation System for Chinese Characters and Its Algorithm Design
-
摘要: 本文针对机械分词,提出词典组织结构、改进的二分法检索、直接匹配算法,以及后缀分词算法。运用这些技术,正逆向切分可共用一部词典,并显著提高分词速度。Abstract: In this paper the structure of a dictionary,improved dichotomic search,direct matching algorithm and postfix word segmenting algorithm are proposed for the implementation of machine seg- mentatiom.Using these techniques,both the forward segmenting and the backward segmenting can share the same.dictionary and the speed of word segmentation will be increased remarkably.
下载: