Constructing Large-Scale Person Ontology from Wikipedia
Yumi Shibaki, Masaaki Nagata, Kazuhide Yamamoto · International Conference on Computational Linguistics · 2010
This paper presents a method for constructing a large-scale Person Ontology with category hierarchy from Wikipedia. We first extract Wikipedia category labels which represent person (hereafter, Wikipedia Person Category, WPC) by using a machine learning classifier. We then construct a WPC hierarchy by detecting is-a relations in the Wikipedia category network. We then extract the titles of Wikipedia articles which represent person (hereafter, Wikipedia person instance, WPI). Experiments show that the accuracy of WPC extraction is 99.3% precision and 98.4% recall, while that of WPI extraction is 98.2% and 98.6%, respectively. The accuracies are significantly higher than the previous methods.