A novel ontology-based semantic similarity measure considering concept height in biomedicine

被引：0

作者：

Sun, Tieli ^{[1
,2
]}

Xing, Yuanyuan ^{[1
]}

Yang, Fengqin ^{[1
,2
]}

Sun, Hongguang ^{[1
,2
]}

Chen, Siya ^{[1
,3
]}

机构：

[1] School of Computer Science and Information Technology, Northeast Normal University, No. 2555, Jingyue Street, Changchun 130117, China

[2] Key Laboratory of Intelligent Information Processing of Jilin Universities, Northeast Normal University, No. 2555, Jingyue Street, Changchun 130117, China

[3] School of Geographical Science, Northeast Normal University, No. 5268, Renmin Street, Changchun 130024, China

来源：

ICIC Express Letters | 2014年 / 8卷 / 05期

关键词：

Semantics;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

The estimation of semantic similarity between terms plays a very important role in document categorization, information retrieval and integration, ontology mapping and so on. Because of the appearance of more knowledge sources and large ontologies such as WordNet and SNOMED CT or MeSH in the Unified Medical Language System (UMLS), more approaches to assess semantic similarity have been proposed. Intuitively, the height feature has an effect on the semantic similarity of concepts and concepts with smaller height are usually more specialized and have more semantic information. In the paper, we propose a new measure combining the height, path length and common specificity of the evaluated concepts. The proposed measure is evaluated against human semantic similarity scores and compared to other existing measures using a standard biomedical ontology SNOMED CT as the input ontology. The experiment results show that the proposed measure has outperformed the path-based approaches and confirm the significance of the proposed measure. © ICIC International 2014.

引用

页码：1281 / 1287