基于双词典机制的中文分词系统设计  

Design of Chinese Word Segmentation System Based on Dual-dictionary Mechanism

作　　者：李玲[1] 

机构地区：[1]中北大学电子与计算机科学技术学院,山西太原030051

出　　处：《机械工程与自动化》2013年第1期17-19,共3页Mechanical Engineering & Automation

摘　　要：中文分词是中文信息处理的基础技术之一,被广泛应用于搜索引擎、机器翻译、自动分类、自动校对、语音合成等方面。阐述了一种基于双词典机制的中文分词系统的设计。该设计中,构造了标准词典、临时词典和临时高频词表组成的双词典机制作为分词基础,应用了正向最大匹配法和逆向最大匹配法进行分词,提出了基于双词典机制的歧义处理方法。实验表明了此设计的可行性和优越性。Chinese word segmentation is one of the basic technologies of the information processing. Chinese word segmentation is widely applied to the search engine, machine translation, automatic classification, automatic correction, speech synthesis and so on. This paper describes the design of a Chinese word segmentation system based on dual-dictionary mechanism. In this design, double dictionary mechanism as a basis for Chinese word segmentation is structured by standard dictionary, provisional dictionary and high frequency word list, moreover forward maximum matching and reverse maximum matching are adopted to segment word, and the ambiguity processing methods based on dual-dictionary mechanism are introduced. Experiments show the feasibility and advantages of this design.

关 键 词：中文分词 双词典机制 歧义处理 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]