Ontology Learning to Realize Intelligent Information Retrieval

• Main Authors: Chong-Lun Liao, 廖崇倫
• Other Authors: Jung-Hsien Chiang
• Format: Others
• Language: zh-TW
• Published: 2004
• Online Access: http://ndltd.ncl.edu.tw/handle/30668760061857496656

碩士 === 國立成功大學 === 資訊工程學系碩博士班 === 92 === 　　An important debate of modern ontology science and technique is how to automatically construct an ontology from the bush of raw data. The traditional methods on constructing domain ontology are manually defining a set of domain terminologies and concepts, and then deciding their relation. However, this task can be lengthy, costly, and controversial because people can have different points of view about the same concept. In this thesis, we develop a new ontology learning method that automatically analyzing and constructing the ontology from domain text. The proposed method utilized several techniques, such as natural language processing and text mining method etc. It comprises three basic stages: the domain terminology extraction, the concepts exploration & concept hierarchy arrangement, and the non-taxonomy relations discovering. We further propose ontology-based intelligent information retrieval system that utilized the resulted ontology to summarize the user query and categorize the retrieval results.