大数据环境下中文词库动态更新系统模型研究  

Research on System Model of Chinese Thesaurus Updates Dynamically under Big Data Environment

作　　者：刘超超[1] 

机构地区：[1]西南科技大学经济管理学院,四川绵阳621010

出　　处：《济宁学院学报》2017年第5期116-119,共4页Journal of Jining University

摘　　要：文本分词以及语义相似度地计算大都依赖于中文词库,而网络的飞速发展产生了很多未收录词库的新词,进而影响了分词的效果和相似度计算的准确性。针对网络时代信息爆炸和新词出现频率高的特性,提出了在大数据背景下动态更新中文词库的模型。依据大数据的特点,提出了备用词研判标准模型,进而以四个子模型为基础提出了词库动态更新模型。The chinese text participle and calculation of semantic similarity mostly depends on the Chinese thesaurus,and the rapid development of the network produces many new words that are not included in the thesaurus,which in turn affects the accuracy of word segmentation and similarity calculation. Aiming at the characteristics of the information explosion in the Internet age and the high frequency of new words,this paper proposes a model to dynamically update the Chinese thesaurus in the background of big data. Based on the characteristics of big data,this paper puts forward the model of the criterion of alternative words,and then puts forward the dynamic updating model of the thesaurus based on the four sub models.

关 键 词：大数据 词库 动态更新 系统模型 

分 类 号：G353.1[文化科学—情报学]