Semantically enhanced Uyghur Information Retrieval Model

Traditional Uyghur search engine lacks semantic information, aiming to solve this problem, a semantically enhanced Uyghur information retrieval model was proposed based on the characteristics of Uyghur language. Firstly word stemming was carried out and web pages were represented by the form of 3-triples to construct the Uyghur knowledge base, then the matching between ontologies and web pages was established by computing concept similarity and relation similarity. Semantic inverted index was built to save the association between semantic entities and web pages, and user query analysis was implemented by expanding the queries and analyzing the relations between the queries, finally by combining the benefits of both keyword-based and semantic-based methods, ranking algorithm was implemented. By comparing with the Google search engine and the Lucene based method, the experiments validate the effectiveness and the feasibility of the model preliminarily. © 2012 ACADEMY PUBLISHER.