Ontology-based Information Retrieval And Applications

With the fast development of the Internet, the amount of information we can get is growing at an exponential rate. At the same time, people usually find themselves lost in the ocean of information. Information retrieval concerns how to efficiently retrieve required information from huge amount of information.Most of the traditional information retrieval systems are based on the mechanical keyword matching technique in the syntax layer. Because machines do not understand the semantics of information, the recall ratio and the precision ratio are inadequate. To solve this problem, the idea of semantic information retrieval was put forward, whose foundation is the concept of ontology.In computer science and information science, an ontology is a formal representation of a set of concepts within a domain and the relationships between those concepts. It is used to reason about the properties of that domain, and may be used to define the domain. In the 2nd chapter of this thesis, many topics on ontology are discussed, including the concept and the meaning, the classification, the method for describing ontologies, and the principle of building ontologies.In the 3rd chapter of this thesis, a framework of ontology-based information retrieval system is proposed. This information retrieval system consists of four modules, which are the user interface module, the search module, the ontology managing module and the resource managing module. And in the 4th chapter, the key techniques involved in that information retrieval system are discussed, including the build method for ontology, the design for search interface, the design for search preprocessor, the application of ontology reasoner and the semantic extension.Finally, a tumor pathology ontology is built, and a journal paper retrieval system based on that ontology is developed. Some preliminary experiments demonstrate that this system can improve the quality and efficiency of information retrieval.