The Department of Electronics and Information Technology (DEITy) has launched what appears to be a prototype effort at a search engine dedicated to service Indian customers not conversant with English. Dubbed Sandhan, the interface currently supports five languages—Bengali, Hindi, Marathi, Tamil and Telugu—and primarily answers queries particular to Indian tourism. It provides an InScript virtual keyboard as well as a transliteration-friendly phonetic option.
Unveiling the search engines for Bengali, Hindi, Marathi, Tamil and Telugu, the Secretary said six years of research has resulted in this milestone but this is only the beginning. He said for making the search engines successful, it is equally important to develop and promote content in Indian languages. Sh Satyanarayana said the real success would be when even village level e-services would be available in local languages.
SANDHAN has been developed by 120 researchers of 12 institutions over a period of 6 years led by Dr. Pushpak Bhattacharya under the supervision of TDIL DeitY. The project aims at satisfying the user information need through text documents present in the web. This search engine captures the information in the form of a query in one of the 5 Indian ‘query’ languages--- Bengali, Hindi, Marathi, Tamil and Telugu. The query is processed to retrieve a set of relevant documents of the same language from crawled data in tourism domain from the World Wide Web (WWW). These retrieved documents are presented to the user in the form of an ordered list based on the relevance of the document.
Although designed mainly for tourism, sectors such as business and academia would also benefit from SANDHAN. It can also be deployed as part of e-governance and e-learning.
The UI is a little buggy and the tourism search results often disappointing (when compared to Google's). But it's a good start. ET has also made an attempt at some dull coverage of this announcement.