E-Paper
IIIT-A all set to develop software for 4 languages
COMPUTING AND reading in languages like Sanskrit, Nepali, Tibetan and Urdu will no more be a utopian thought for persons of different lingual backgrounds with Allahabad's Indian Institute of Information of Technology (IIIT-A) all set to take on the task of developing a software and Optical Character Reader (OCR) for the four languages.
COMPUTING AND reading in languages like Sanskrit, Nepali, Tibetan and Urdu will no more be a utopian thought for persons of different lingual backgrounds with Allahabad's Indian Institute of Information of Technology (IIIT-A) all set to take on the task of developing a software and Optical Character Reader (OCR) for the four languages.
In a recent development, the Union Ministry of Communication has entrusted IIIT-A with the challenge of developing a software which would facilitate computing operations in Sanskrit, Urdu, Tibetan and Nepali.
"The uphill task of translation of less-spoken languages like Tibetan and Sanskrit has been entrusted upon us by the Ministry of Communication as it deemed us capable of undertaking a difficult and a challenging mission like this," said IIIT-A Director Dr Murli Dhar Tiwari in an exclusive chat with HT Allahabad Live.
Dr Tiwari said that a formal communication in this regard was received recently at IIIT-A specifying the sanctioning of Rs 1.50 crore for the project.
The said translations will be carried out by ultra-modern Universal Digital Lab (UDL) which is equipped with highly sophisticated software and equipment needed for the project.
"The primary work has already begun and intricate phase of the project will be implemented after the procurement of necessary of equipment, database and experts," Dr Tiwari said.
It is worth mentioning that the Union Ministry of Communication is working for the promotion of languages like Sanskrit and Tibetan in the country. The test endeavour envisions the enrichment of these languages and its translation in globally spoken languages.
"The project will involve language experts, people dealing in logistics and technologists," informed Dr Tiwari.
He added that it would be miraculous marriage of two different streams of literature and technology.
Outlining the contours of the project, Dr Tiwari said that experts of language concerned would present the requisite information needed for the translation from one language into another.
"The technology experts will take care of the scripting and conversion of the script of the language into the script of desired language. This would be possible with the development of Optical Character Reader," he said.
The Optical Character Recognition (OCR) is the process of converting scanned images containing texts into a computer processable format such as ASCII, ISCII, and UNICODE etc.
Dr Tiwari said that procurement of experts and necessary equipment would be made soon and efforts will be made to recruit the best available experts of various fields for the project.
He also maintained that a group of different institutions including one based at Hyderabad was working on Urdu and therefore understanding could be reached with institution for collaboration on the project.
