Author Login Editor-in-Chief Peer Review Editor Work Office Work

Computer Engineering ›› 2012, Vol. 38 ›› Issue (7): 57-59,69. doi: 10.3969/j.issn.1000-3428.2012.07.019

• Networks and Communications • Previous Articles     Next Articles

Query Expansion Method Based on Ontology and Local Context Analysis

Aiming at the problem of semantic boundary determination difficulty in semantic query expansion, this paper proposes a method of query expansion based on ontology and local context analysis. It filters the candidate expansion concepts according to the local context on the basis of acquiring candidate expansion concept based on ontology expansion, improves the filter function and filters expansion words twice. Experimental results indicate that the query performance of the method is improved greatly compared with the ontology based query expansion method.   

  1. (School of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, China)
  • Received:2011-07-15 Online:2012-04-05 Published:2012-04-05

基于本体和局部上下文分析的查询扩展方法

语义查询扩展中存在语义边界确定困难的问题。为此,提出一种基于本体和局部上下文分析的查询扩展方法。在本体扩展得到候选扩展概念的基础上,改进筛选函数,结合局部上下文对候选扩展概念集进行二次筛选。实验结果表明,与基于本体的查询扩展方法相比,该方法的查询性能较高。   

  1. (兰州理工大学计算机与通信学院,兰州 730050)
  • 作者简介:王旭阳(1974-),女,副教授、硕士,主研方向:数据挖掘,模式识别,智能信息处理;萧 波,硕士研究生

Abstract: Aiming at the problem of semantic boundary determination difficulty in semantic query expansion, this paper proposes a method of query expansion based on ontology and local context analysis. It filters the candidate expansion concepts according to the local context on the basis of acquiring candidate expansion concept based on ontology expansion, improves the filter function and filters expansion words twice. Experimental results indicate that the query performance of the method is improved greatly compared with the ontology based query expansion method.

Key words: ontology, query expansion, local context, entity relativity, co-occurrence frequency

摘要: 语义查询扩展中存在语义边界确定困难的问题。为此,提出一种基于本体和局部上下文分析的查询扩展方法。在本体扩展得到候选扩展概念的基础上,改进筛选函数,结合局部上下文对候选扩展概念集进行二次筛选。实验结果表明,与基于本体的查询扩展方法相比,该方法的查询性能较高。

关键词: 本体, 查询扩展, 局部上下文, 实体相关度, 共现频度

CLC Number: