Conceptual Indexing and Knowledge Extraction Based on Automatic Construction of Ontology

• Main Authors: Guan-Sian Lee, 李冠賢
• Other Authors: Shian-Hua Lin
• Format: Others
• Language: zh-TW
• Published: 2010
• Online Access: http://ndltd.ncl.edu.tw/handle/87589249923448129529

碩士 === 國立暨南國際大學 === 資訊工程學系 === 98 === As the explosive growth of the Web content, reading pages, documents, or the currently hot eBook from the Web becomes one of the major styles that people learn or acquire knowledge. However, the eBook technology focuses on simulating the way of traditional reading of books on the eBook reader. Readers still word-by-word read the book content. As the book content is digitized, more intelligent services for reading ebooks should be proposed. If the system can previously analyze the content, build the book’s semantic ontology, and create indexing information; then the system may provide Knowledge Map for readers so that they can realize the overview of the book by taking a glimpse. In this thesis, we integrate techniques of data mining, search engine, and web information processing to develop an intelligent system that automatically analyze the book textual content, extract significant concepts, explore conceptual relations, and build the book ontology as an extension of the book’s learning map. In this way, readers can rapidly understand the book’s content. Based on SVG (Scalable Vector Graphics), we provide the graphical Knowledge Map to readers for realizing relations among people, events, times, places, and things.