In early 2023, the vision to make Punjab Vidhan Sabha debates digitally accessible took shape. Today, this effort has become a reality through a collaborative project between Punjabi University, IIIT Hyderabad, and C-DAC Noida, under the NLTM Bhashini Project, funded by MeitY.

Transforming Parliamentary Access

Led by Dr. Gurpreet Singh Lehal (Retired Professor, Punjabi University Patiala & Senior Project Consultant, IIIT Hyderabad) and Prof. C.V. Jawahar (IIIT Hyderabad), this initiative brings searchable access to debates dating back to 1947. C-DAC Noida provided crucial software infrastructure, ensuring efficiency and scalability.

To develop the search engine, the extensive archive of the Punjab Vidhan Sabha, comprising over two lakh pages of debates spanning 77 years, was systematically digitized and converted into Unicode. The team overcame various technical challenges, including:

• Digitization of fragile, historical documents
• Recognition of multiple scripts (Devanagari, Gurmukhi, and English)
• Development of an advanced Optical Character Recognition (OCR) system for diverse fonts
• Optimization of the search engine for linguistic accuracy

The search engine was officially launched on 11th March 2025 by Punjab Vidhan Sabha Speaker, S. Kultar Singh Sandhwan, marking a significant milestone in democratizing legislative records

During the event, Dr. Gurpreet Singh Lehal provided a comprehensive demonstration of the search engine’s capabilities, addressing queries from ministers and officials. Additionally, Krishna Tulsyan presented the Audio Books application for visually impaired individuals, showcasing its integration with the search engine and its role in enhancing digital accessibility.

Key Features of the Punjab Vidhan Sabha Search Engine

• Retrieval of Legislative Debates - Users can instantly search for discussions on any topic, such as “Punjabi Suba”, retrieving debates from 1947 onwards.
• Multilingual Search Support - The search engine supports English, Hindi, and Punjabi, ensuring comprehensive access.
• Fuzzy Search for Enhanced Accuracy - The system recognizes similar-sounding words and auto-corrects minor spelling errors in names or topics (e.g., “Sardar Partap Singh Kairon” will match “Pratap” as well)
• Filtering by Assembly and Date - Users can refine searches by Vidhan Sabha sessions or set custom date ranges for precise results.
• Download and Print Functionality - Digitized debates can be easily downloaded or printed for research and archival purposes.
• Promoting Transparency and Good Governance - By making legislative records publicly accessible, the search engine empowers policymakers, researchers, and citizens.

Key Contributors

This project was made possible by:

• IIIT Hyderabad Team: Dr. Gurpreet Singh Lehal, Prof. C.V. Jawahar, Krishna Tulsyan, Ajoy Mondal, Aradhana Vinod
• Punjabi University Patiala Team: Prof. Dharamveer Sharma, Dr. Tejinder Singh Saini, Dr. Ankur Rana, Ms. Dalwinder
• C-DAC Noida Team: Karunesh Arora, Tushar Patnaik, Bhupender Singh
• Punjab Vidhan Sabha IT Team: Implementation and Deployment