Tool to detect plagiarism in Indian languages
Tribune News Service
Patiala, October 30
Two professors, one from Punjabi University and another from DAV College, Jalandhar, have received the copyright for ‘Shodh Mapak’, a plagiarism detection tool for Indian language documents with special focus on Hindi and Punjabi.
A total of three universities, including the Panjab University, Chandigarh, Guru Nanak Dev University, Amritsar, and Punjabi University, Patiala, have also endorsed the working of the first such India-made software devised under the Make-in-India initiative.
Dr Vishal Goyal, associate professor at the department of computer science, Punjabi University, said the two got a grant of Rs 20 lakh from the Ministry of Electronics and Information Technology (MEITY) for the software for Punjabi and Hindi texts in September 2017. “The URKUND software used by universities after adoption by the UGC has been purchased from a Swedish company. The MHRD should adopt this software to fulfil the dream of using Make-in-India products.”
The basic software is independent from languages and all sources including previously written thesis, books, and manuscripts of a particular language have been added thereafter. The two emphasised on open source technologies, including extracting text of Indian languages from PDF files among others.
The software has its own repository of thesis projects made available from various sources. Dr Goyal said, “We went to a number of places to procure formerly written texts to add them in the project. This includes Punjabi Sahitya Academy, using the reservoir available on Shodhganga, an online reservoir of Indian languages among others. There are a few such software on the market but none of them is Indian made and they also do not have a reservoir to match the text with.”
The consortium of 12 institutions, including Punjabi University as its leader, has proposed to extend the software in the remaining Indian languages under the UGCs STRIDE scheme.
Dr Rajeev Puri, assistant professor at DAV college, Jalandhar, said the team, including Jitesh Pubreja, senior computer programmer and Jaswinder Singh, a linguist, has applied for a grant of Rs 3.5 crore for the extension.
Shodh mapak software
- The ‘Shodh Mapak’ software has its own repository of thesis projects made available from various sources.
- The basic software is independent from languages and all sources including previously written thesis, books, and manuscripts of a particular language have been added thereafter
- The consortium of 12 institutions, including Punjabi University as its leader, has proposed to extend the software in the remaining Indian languages under the UGCs STRIDE scheme
