Please use this identifier to cite or link to this item:
Title: Acquisition of domain concepts and ontology construction
Authors: Cui, Gaoying
Degree: Ph.D.
Issue Date: 2010
Abstract: Ontology is an area of research that gets off to a flying start and attracts inceasing attention in many branches of computer science as well as other relevant subjects. As a knowledge structure, ontology can be applied to different areas where domain knowledge is needed. Avoiding the weak points of manual methods of constructing ontologies in the top-down direction, such as time consuming and difficult to update, automatic or semi-automatic ontology construction methods usually start from the bottom with the acquisition of domain concepts from a proper corpus and then build the relations among these concepts. In this research, a series of studies have been conducted and the whole work can be divided into two aspects include the work for bottom-up construction of ontology and top-down construction of ontology. For bottom-up ontology construction, FCA method is used first to build an domain ontology, the focus of this method is to select an appropriate attribute set for the given object set. Considering the limitation of FCA method, Wikipedia, the world's largest online encyclopedia, is exploited for the acquisition of the corpus. Then, based on the Wikipedia, concepts and attributes are extracted according to the context information and instance information in Wikipedia, such as the {{Infobox}} structures, definition sentences, and category labels. For top-down construction of ontology, domain terms that are labels of concepts are classified through given Part-of-Speech tags as prilimiary classification information.
Subjects: Hong Kong Polytechnic University -- Dissertations
Data mining
Knowledge acquisition (Expert systems)
Ontologies (Information retrieval)
Pages: x, 147 leaves : ill. ; 31 cm.
Appears in Collections:Thesis

Show full item record

Page views

Last Week
Last month
Citations as of Sep 17, 2023

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.