Ontology Similarity Computation Use Ranking Learning Method

被引：0
作者：
Wang Yaya [1 ]
Gao Wei [2 ,3 ]
Zhang Yungang [2 ,4 ]
Gao Yun [5 ]
机构：
[1] Binzhou Polytech, Dept Informat Engn, Binzhou, Shandong, Peoples R China
[2] Yunnan Normal Univ, Dept Informat, Kunming, Yunnan, Peoples R China
[3] Soochow Univ, Dept Math, Suzhou, Jiangsu, Peoples R China
[4] Univ Liverpool, Dept Comp Sci, Liverpool L69 3BX, Merseyside, England
[5] Yunnan Normal Univ, Dept Editorial, Kunming, Yunnan, Peoples R China
来源：
2011 INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTATION AND INDUSTRIAL APPLICATION (ICIA2011), VOL III | 2011年
关键词：
ontology; similarity computation; ranking; hinge loss function; convex quadratic program;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Ontology similarity calculation is an important research topic in information retrieval. By analyzing the classical vertices ranking algorithm on graph, we propose that the weight functions and 2 function can be designed based on the structure of ontology. Via the ranking learning algorithm, the ontology graph is mapped into a line consists of real numbers. The similarity between two concepts then can be measured by comparing the difference between their corresponding real numbers. Experimental results show that the proposed algorithm has high accuracy and efficiency.
引用
收藏
页码：20 / 23
页数：4
相关论文
共 15 条
  • [1] Agarwal S., 2006, P 23 INT C MACH LEAR, P25, DOI [DOI 10.1145/1143844.1143848, 10.1145/1143844.1143848]
  • [2] Alexander Rong Y., 2006, CIVR, P113
  • [3] [Anonymous], 2002, P ACM SIGKDD KDD 200, DOI 10.1145/775047.775067
  • [4] [Anonymous], 1996, Spectral Graph Theory
  • [5] Belkin M., 2004, P 17 ANN C LEARN THE
  • [6] BOUZEGHOUB A, 2006, IBIS, V1, P73
  • [7] Boyd S., 2004, CONVEX OPTIMIZATION, VFirst, DOI DOI 10.1017/CBO9780511804441
  • [8] CHUA TS, 2005, TRECVID 2005 NUS PRI
  • [9] Corinna C., 2007, P 24 INT C MACH LEAR
  • [10] Craswell N., 2003, P TEXT RETR C TREC
12