Indian Institute of Technology, Bombay is working on a new search engine that would trawl the web and provide relevant answers to queries like â€˜how old is Feng Shuiâ€™, â€˜how many people are infected with AIDS worldwideâ€™, â€˜how old is Feng Shuiâ€™, â€˜how many people are infected with AIDS worldwideâ€™, â€˜length of the Nile Riverâ€™, â€˜maximum speed of a Mercedes-Benz SLR McLarenâ€™, or â€˜driving time between Delhi and Jaipurâ€™.
The idea is that unlike the existing search engines that expect 2-3 word queries and return URLs to browse, the new engine should be able to understand structures in the query and respond with information nuggets and tables, and not just the links of the pages from which this knowledge is distilled. The IIT-B team has already created billions of annotation links between a 500-million web page corpus and millions of entities known to Wikipedia.
The project is being headed by Professor Soumen Chakrabarti of IIT-Bâ€™s Computer Science Department, which has received a research grant from Hewlett-Packard (HP) Labs. Microsoft Research has provided additional research funding, while Yahoo has donated a number of high-end servers. Chakrabarti and his team plan to release their new search API to key research partners, including several universities, by the end of this year. [Source: Business Standard]