摘要
概念空间方法就是自动构造概念语义网络 ,并以此为基础进行概念检索的一种方法。它的目标是建立一个知识丰富的、可理解的概念空间 ,可以代表所在信息空间中的概念及两两之间的关联。具体包括 :确定研究领域 ,训练文档收集 ;数据预处理 ,信息过滤和自动标引 ;共现分析 ;联想检索四个阶段。概念空间技术通过词语相似度计算 ,辅助用户选择检索词 ,促使用户快速、准确地定位所需要查找的信息。笔者对其中部分算法进行模拟和实验 ,实验表明这种技术具有可行性。
Concept space method is an approach of information retrieval.Concept space is composed of natural language terms、controlled vocabulary terms and their aboutness.Concept space has the following functional tasks:selecting a domain of discourse;searching training text sets;pre-processing the data set,filtering information and automatic indexing;association retrieval.By means of co-occurrence analysis to provide the mapping from the natural terms of the user's query to the control terms used in a given database,to help the user in selecting the proper control terms in the process of searching database.The author simulates and makes testing on parts of algorithms towards some of problems,proves their feasibility.
出处
《情报科学》
CSSCI
北大核心
2004年第4期470-474,共5页
Information Science
