Tác giả: Nguyễn Bảo Ân. Prof. Don-Lin Yang (Người hướng dẫn Khoa học).

Trường ĐH Phùng Giáp. Năm XB: 2011. Mô tả: 69Tr, kích thước: 21x29 cm. Số định danh: 005.7/ A121. Vị trí: Phòng Tài nguyên nội sinh.

Tóm tắt:

Ontology is an effective formal representation of knowledge used commonly in artificial intelligent, semantic web, software engineering, and information retrieval. Typically, ontologies are constructed by domain experts using domain knowledge and relevant documents. However, manual acquisition of ontologies from domain documents consumes large costs.

In this research we present a support system for Vietnamese ontology construction using pattern-based mechanisms to discover Vietnamese concepts and conceptual relations from Vietnamese text documents. As there are very few existing taxonomies constructed in Vietnamese, we use non-taxonomy based approach. The combination of association rule mining and lexical pattern based learning was used as our main method of concept extraction and conceptual relation detection. We employ GATE (General Architecture for Text Engineering) as an efficient tool for lexical pattern based extraction by taking advantages of its transducer and JAPE grammar. A Vietnamese smartphone ontology is built to demonstrate the result of our proposed system.