Semantic Document Retrieval in a Heterogeneous Datalake

Project Principal Investigator(s): Apurva Kulkarni

PI:Prof. Chandrashekar Ramanathan

The objective of the proposed work ‘Semantic Document Retrieval in a Heterogeneous Datalake’ is to enhance the document retrieval system by incorporating a deeper understanding of the underlying cognitive aspects of search intent. The proposed work is implemented over data from the Government of Karnataka. The work includes experimentation with real-world search queries to demonstrate the practicality and effectiveness of the proposed system. By leveraging semantic understanding and domain knowledge, the system aims to bridge the gap between the user’s search intent and the documents retrieved in the document retrieval environment.