Research on Web Cross Language Information Retrieval Based on Domain Ontology

With the increasingly rich of Web resources, people need to cross-language information and knowledge sharing, cross-language information retrieval (CLIR) research on such problems. This paper brings forward a Web cross language information retrieval model based on the domain ontology. The model basing on the technologies of traditional information retrieval, use domain ontology to describe the relevant domain knowledge in different kinds of languages, comprehend and extend query terms, lead the retrieval rise to semantic level. The main ideal and methods of the model are described in detail, and through experiment to validate our approach. The experiment are designed to retrieval travel news in Chinese from Sina website with query in English, its results prove that this model can improved the average precision/recall of retrieval to certain extent.