A Semantic-Based Information Retrieval System

Abstract

Information retrieval (IR) is the process of retrieving relevant documents from a large collection of documents. The applications of these technologies are no longer restricted to only online search engines, instead these are widely being used by organizations to facilitate different organizational information searches. Efficient retrieval of documents from a large collection of organizational data is still a challenging task. In this paper, a semantic-based information retrieval system is presented for institutional student project report retrieval. The model uses a clustering-based technique for fast document retrieval and a semantic-based query processing technique for retrieving the most relevant documents with respect to the user query. A number of tests were conducted to evaluate the performance of the presented model on different random user queries, and the precision and recall measures were determined. The performance of the model is also compared with existing retrieval techniques, and the results obtained show the efficiency of the model in providing relevant documents quickly. The model achieves approximately 91% precision and 90% recall accuracy in the considered domains and data set.