文本挖掘与中文文本挖掘模型研究  

Study on the Text Mining and Chinese Text Mining Framework

作　　者：谌志群[1] 张国煊[1] 

机构地区：[1]杭州电子科技大学计算机应用技术研究所,浙江杭州310018

出　　处：《情报科学》2007年第7期1046-1051,共6页Information Science

基　　金：浙江省自然科学基金项目(M603025)

摘　　要：文本挖掘,又称为文本数据挖掘或文本知识发现,是指在大规模的文本中发现隐含的、以前未知的、潜在有用的模式的过程。本文首先对文本挖掘进行了概述,给出了文本挖掘的定义、特点和研究现状。然后对国内中文文本挖掘的研究现状进行了分析,指出了当前中文文本挖掘研究中存在的主要问题和主要研究方向。最后提出了一个统一的中文文本挖掘模型——UCT-MF。该模型具有层次性、开放性和可扩展性,为中文文本挖掘系统提供了基本体系框架。Text mining, also known as text data mining or knowledge discovery in texts, focuses on computerized exploration of large amounts of text and on discovery of implicit, previously unknown, and potentially useful patterns within them, Firstly, the text mining are introduced including its definition, its characteristics and its progress. Then, The problems and research direction of Chinese text mining are pointed out based on analysis for state- of- the - art of research on Chinese text mining. Finally, Unified Chinese Text Mining Framework （UCTMF） is presented. The framework are hierarchical, open, and scalable. It provide a unified and public frame for Chinese Text Mining System.

关 键 词：文本挖掘 数据挖掘 中文文本挖掘模型 中文信息处理 

分 类 号：G354[文化科学—情报学]