IIT Bombay launches AI-based translation ‘Project Udaan’

In due course, textbooks in all domains can be taken up for translation

As India celebrated Hindi Diwas, the Indian Institute of Technology-Bombay rolled out ‘Project Udaan’, which enables translation from English to Hindi and all Indian languages of textbooks and learning materials in engineering and all main streams of higher learning.

Institute Chair Professor, Department of Computer Science and Engineering, IIT Bombay, Prof. Ganesh Ramakrishnan, and his team launched the Project Udaan at a virtual event in which Principal Scientific Adviser to the Government of India, Dr Krishnaswamy VijayRaghavan was the chief guest.

‘Project Udaan,’ a donation-based project, is an end-to-end ecosystem, which translates scientific and technical content from English to Hindi and all other Indian languages.

Prof. Ganesh and his team have built an AI(Artificial Intelligence)-based translation ecosystem, which can help translate engineering textbooks and learning materials in one-sixth the time it would take for a team consisting of domain and linguistic experts working manually.

In due course, textbooks in all domains can be taken up.

Prof Ganesh said: "Our approach to machine translation has been that it will be aided by human effort. We started building lexicons of various technical domains. Here we faced the challenge of digitising the bilingual dictionaries and glossaries produced by the Commission for Scientific & Technical Terminology (CSTT).”

"We have developed very robust bilingual OCR technology and several post-editing tools by which we now have access to digital bilingual dictionaries in machine-readable format. We are therefore able to use the appropriate scientific and technical terms available in Hindi instead of transliterating the English terms.

"We are happy to state that by deploying our AI-based Translation Engine, we are now able to translate a technical book in less than one-sixth the time it would take for a team consisting of domain and linguistic experts working manually. In due course, as our AI and ML engine learns with every page and every book being edited in each domain, we expect to achieve a much shorter turnaround time,” he added.