An Automatic Method for WordNet Concept Enrichment using Wikipedia Titles

• Published in: Reliable and Autonomous Computational Science pp. 347 - 365
• Main Authors: Hwang, Myunggwon, Choi, Dongjin, Ko, Byeongkyu, Choi, Junho, Kim, Pankoo
• Format: Book Chapter
• Language: English
• Published: Basel Springer Basel 2010
• Series: Autonomic Systems
• Subjects: Context Information; Noun Phrase; Proper Noun; Query Answering; Semantic Relation
• ISBN: 9783034800303; 3034800304
• DOI: 10.1007/978-3-0348-0031-0_18

Knowledge bases such as WordNet are positively utilized for semantic information processing. However, much research indicates that the existing knowledge bases cannot cover all of concepts used in talking and writing in real world. To solve this limitation, this research suggests a method which enriches WordNet concepts through analyzing Wikipedia document set. Wikipedia currently contains documents more than 3.2 million and it describes tangible and intangible objects in detail. Moreover, it is continuously grown with new subjects and contents by domain-specific specialists. Therefore, the Wikipedia contents can be usefully used for knowledge base enrichment. This paper describes semantic method which conceptualizes titles of Wikipedia documents and which gives a connection between the title concepts and WordNet concepts. Through the experimental result, we could get better precision than that of existing similar method.