Intelligent Search in Digital Documents

Distributed repositories, containing digital documents are usually maintained and managed independently according to organization/users own requirements. Same information (i.e. documents containing same information) in different repositories, may be represented differently, makes it hard to retrieve desired information. Keyword based information retrieval technique helps in improving recall of user query result, but having low precision. To improve precision, we adopt semantic information retrieval technique. We are proposing architecture for semantic based information retrieval, in which plain text is read semantically and the extracted metadata is stored and later used for semantic search.