摘要
在分析关键词、主题词间共现关系的基础上,提出了同义关键词间存在"互斥互信"的理论,并根据这一理论设计了相应的统计模型,从复杂的词间共现关系网中,识别出同义关键词。实验结果表明这种识别方法能有效识别出词形不同的同义词,并具有较高的准确率和可操作性。
After the relation between co-occurrence of key words and subject headings was analyzed, the ＂mutual exclusion and mutual trust＂ theory in synonymous key words was proposed, based on which, a corresponding statistical model was designed and synonymous key words were identified from the co-occurrence relation net between complicated words. The results showed that this method could effectively identify the different morphological synonyms with a rather high accuracy and maneuverability.
出处
《中华医学图书情报杂志》
CAS
2012年第5期1-4,共4页
Chinese Journal of Medical Library and Information Science
基金
教育部人文社会科学研究一般项目"共现词汇语义关系挖掘与本体自动构建研究"(10YJC870051)
广东高校优秀青年创新人才培育项目"基于词共现的关键词语关系自动识别研究"(wym09089)
关键词
同义词
自动识别
共现词组
主题词
Synonym
Automatic identification
Co-occurrence words
Subject heading
