摘要
为了解决关键字信息检索语义缺失问题,提出了一种基于相关度的关键词语义信息检索方法。该方法通过考查文档中的词语、概念之间关系(内在联系)和文档与文档之间关系(外部联系)的相关度,提出了一种词语-概念相关度的改进方法;然后,将改进的方法引入到经典的统计语言模型中,得到一种基于NKTCM方法的统计语言模型(KCSLM)。最后,形成了完整的基于语义的关键字信息检索模型(KIRBS),实现了语义处理、信息处理、信息组织与存储和结果排序4部分功能。实验证明。该方法具有很高的准确率和召回率,并同时具有较高的执行效率。
To deal with the problem of semantic missing during keyword retrieval.The retrieval approach was proposed on a relevance-based keyword semantic information: Firstly,an improved word-concept relevance method which measures the relevance between word and concept by considering both the internal and external correlations,was proposed;Next,by importing the improved word-concept relevance method into the classical statistical language model,a new statistical language model which is based on NKTCM method,was proposed.Then,the semantic-based keyword information retrieval model(KIRBS) was formed,which realized four functions: the semantic processing,information processing,information organization,storage and results-sorting.The experimental results prove that our approach presented in this paper has an high recall and precision and good efficiency as well.
出处
《辽宁工业大学学报(自然科学版)》
2012年第5期288-294,共7页
Journal of Liaoning University of Technology(Natural Science Edition)
关键词
本体
关键字
信息检索
语义相关度
ontology
keyword
information retrieval
semantic association