MALLESWARAM:Partha Pratim Talukdar of the Indian Institute of Science is one of the 11 recipients of the Accenture Open Innovation Grant announced this month.
He is attached to the Supercomputer Education and Research Centre (SERC) in IISc. The award includes financial assistance as well as an opportunity to collaborate with scientists in Accenture.
This year, the 11 grants go to scientists at leading universities across the world, including four from India — IISc, IIT-Madras, IIT-Bombay and BITS, Pilani.
Talukdar’s research is based on the concept that when we read a book or watch a movie, our brain processes the sensory input and uses pre-acquired background knowledge to enrich our understanding of the content.
Such background knowledge is normally not available to computers, and the absence limits their ability for automated tasks such as translation of a document from one language to another.
Take a search engine: it cannot really understand all that is stored on web pages across the Net. With the help of Talukdar’s work, it will comprehend more.
“When we tell a family member to make us a cup of coffee, they go straight to the kitchen as they know that coffee is associated with the kitchen. Let us say we have a robot for household chores. When we ask it to go and get a coffee, it will not know where to go unless that knowledge is given to it. My work is in this area,” Talukdar told City Express.
Computers cannot understand English or Spanish, or follow the information contained in them either. “Here is where I come in. I try to make the knowledge present in webpages, blogs and emails accessible to these machines and computers automatically, with minimum human input,” he said.
“We at Accenture Technology Lab are very excited to award the University Grant to IISc Bengaluru. I am certain the outcome of the joint research will further advance our thought leadership,” said Sanjay Podder, Managing Director and Head for Software Engineering Research at the Accenture Technology Lab.
Talukdar’s main research interests are in natural language processing, machine learning, and cognitive science. He holds a PhD from the University of Pennsylvania, and has had post-doctoral research experience at the Carnegie Mellon University.
He joined the IISc faculty last year and has established the Machine And Language Learning (MALL) Lab.
Talukdar’s work is particularly relevant in the Indian context as the country has huge volumes of textual content in multiple languages.
A related research interest of Talukdar is to study the cognitive processes in the brain when it deals with language. Making use of brain imaging techniques such as MRI, he is trying to understand how the brain searches its store of knowledge while reading a text document.
Such techniques, he believes, can be borrowed or adapted in designing algorithms for computers. For this purpose, he has been collaborating actively with neuroscientists at the IISc and outside.