While most enterprise data is unstructured and file based, the need for access to structured data is increasing. In order to reduce the cost for finding information and achieve relevant results there is a need to build a very complex query which indeed is a serious challenge. Data volumes are growing at 60% annually and up to 80% of this data in any organization can be unstructured. In this paper we focus on describing the evolution of some modern ontology-based information retrieval systems. Further, we will provide a brief overview of the key advances in the field of semantic information retrieval from heterogeneous information sources, and a description of where the state-of-the-art is at in the field. Finally, we present and propose a novel use of semantic retrieval model based on the vector space model for the exploitation of KB (Knowledge Base) to enhance and support searching over robust and heterogeneous environments.
ontology, information retrieval, semantic web, knowledge base.