Skip to main content
Industrial Research And Consultancy Centre

Information extraction and retrieval

Information extraction (IE) is the task of automatically extracting structured information from unstructured and/or semi-structured machine-readable documents, while information retrieval (IR) is finding material (usually documents) of an unstructured nature (usually text) that satisfies an information need from within large collections (usually stored on computers), using queries.The Centre for Indian Language Technology (CFILT) at IIT Bombay has a long-standing research in both information extraction and retrieval.

Word sense disambiguation

Word sense disambiguation (WSD) deals with computationally resolving ambiguities in a text. Languages have many polysemous words i.e. words having more than one meaning or sense. WSD is the process of identifying the correct sense of a word in a particular context. For instance, consider the sentence, ‘Ram is playing cricket in the park’, where the word ‘cricket’ is ambiguous with two senses: ‘a game’ and ‘an insect’.

Towards a critical edition of the Kasikavrtti

To bring out a critical edition of a text entitled Kasikavrtti written in the 7th century CE. This is a commentary on the celebrated Sanskrit grammar of Panini. Kasikavrtti is the oldest complete commentary on the grammar of Panini. We prepare the edition based on more than 200 manuscript evidences of this text written in more than 8 Indian scripts like grantha, sharada, nigari, etc., and found in the entire Indian subcontinent as well as outside (like US, UK, Germany, France, etc.)

Swarachakra: Keyboard for typing in Indic scripts on Android

Text input in Indian languages on mobile phones has many challenges. Not surprisingly, text input on computers and mobile devices in India is still predominantly in English. But only a small minority of Indians can read or write in English. This is a major barrier in the wider adoption of digital technologies by such users. Our research aims at designing easy-to-use text input mechanism sto enable Indians to type in their mother tongue.

Smart Solution for Smartphones?

Anybody who migrates to smart phones soon begins to question the smartness of it all. While batteries lasted a fortnight or so in vanilla mobile phones, a smartphone typically empties the battery in less than a day. Carrying those bulky rechargers is a remedy worse than malady. How do you power your smart phone for days when you are nowhere near a power source?

The Gigabit Networking laboratory at IIT Bombay has been instrumental in two key technology developments in the telecom arena: the CESR and the TCC.

The CESRs: A telecommunication technology called Carrier Ethernet Switch Routers or CESRs was developed by the Gigabit Networking Laboratory at IIT Bombay. The goal of CESRs was to facilitate telecom service providers to move large chunks of data through its network by acting upon data headers at various levels of service offerings. The first indigenously conceptualized, designed, fabricated and patented CESRs were rolled out in Spring of 2011, and the launch customer for the CESRs was MTNL. MTNL built two data-centers, in Mumbai commissioned in May 2011 that used the CESRs.

Jammer Proofing Communication Systems

A theoretical study from IIT Bombay can help make our military communication more robust

The security and reliability of communication systems used in military applications are uncompromisable. Jammers can disrupt radio communication in a locality; a strategy the military is shown to use while attacking terrorist camps in a recent movie. Knowing how jammers behave in various conditions becomes significant.

Mining the Treasures of Twitterverse

Researchers develop a search system to extract meaningful data from live social media posts

Ever tried searching ‘goal’ or ‘kick’ on Twitter during the interval of a football world cup match? You were probably trying to find out who scored the goal on a penalty kick in the first half, and chances are that search results also have content about life goals and a kick from coffee!

Urban transportation modeling system for sustainable city

To evaluate any urban transportation system based on economic, environmental and social sustainability indices, one needs a modeling system that replicates the behaviour of travellers under various land use and transportation scenarios. As a part of my research such modeling systems have been developed for our cities. These models should be sensitive to the short-term decisions of individuals, such as choice of transport mode, route and departure time; medium to long term decisions like choice of work place and residence; and land use policies of the planning bodies.