Name Tamil Valarch Kazhagam on Campus Chepauk University of Madras | Photo Credit: M. Srinath
There is no lack of Tamil content on the Internet, but virtually negligible volume is searchable because it avoids the algorithm of artificial intelligence (AI), unlike English.
To solve this gap, Tamil Valarchi Kazhagam (Tamil Academy), a non -governmental body of scientists, took over the project to convert the content available on the Internet into a searchable matter using optical character recognition (OCR).
“The problem of Tamil’s content is that it is all in the form of a scanned version or pictures or PDF. You can keep this matter as a photo. If it is not converted to the format of words, you cannot have a search data in Tamil,” says M. Rajendran, President of the Academy and former Chancellor Tamil University.
Rajendran, who pointed to the Academy, has associated with Wikipedia and the central Institute of Classic Tamil, he says he plans to train 30 postgraduate students, attracted from various institutions in Chennai and his surroundings, for three to seven days in a verbal convert, all freely available on the net. This includes materials located by the State Government in the public sphere after obtaining copyright and those that have no copyright problems.
The training program will be held in October will allow students to correct errors that can crawl during the content transfer process. “After some time, selected students can continue their task from their homes. We will provide them with motivation,” he says. If necessary, the educational program can be expanded to districts.
The Academy, which entered the 80’s year at the end of this month, was founded by former Minister of Education TS Avinashilingam Chettiar in 1946 under the Act on Registration of Companies. Former Minister of Trade Unions for Domestic Affairs and Finance P. Chidambarama is the chairman of the Board of Directors Tamil Valarchi Kahagam, who since its foundation has been operating from the campus Chepauk University of Madras.
So far, the body has brought 10 volumes of Tamil encyclopedia, the same number of volumes for children’s literature, 13 volumes about medicine and seven volumes on Siddha medicine. Former Minister of Trade Unions for Agriculture and Food C. Subramaniam and veteran VC Kalandaisamy led the academy. A few months ago, Chief Minister Tamil Nadu MK Stalin presented a check for CRORE 2.15 GBP boss Tamil Valarchi Kazhagam as a help government for smooth functioning of the body.
In addition to the project to make Tamil Valarchi Kazhagam Tamil AI, six other-Slovak students (Tamil-Tamil-English); universal catalog covering Tamil books and publications on Tamilogly; Collection of articles published by academies on Tamilogy; mining of new Tamil words; Encyclopedia of thoughts in Tamil and others on Tamil dramaturgy.
Rajendran, who has developed, says the dictionary is designed for children of Tamil’s diaspora. The catalog will help book lovers to find out where the titles of their choice are available in which library and in which country. As for the encyclopedia of thoughts in Tamil, it explains that “we do not get into the area of identification of the age in which the idea has evolved.” With the exception of the dictionary, the remaining projects will be completed in eight months. The dictionary project may take a year, adds Dr. Rajendran.
Published – September 2025 05:07
