The Natural Language Processing (NLP) group focuses on developing Tools, Technologies, Products and Systems to facilitate the use of computers and the Internet for day-to-day life. In the Indian context, finding ways of making e-information accessible non-English knowing persons constitutes a major aspect of such work. The group also works on building lexical resources such as dictionaries, WordNet and tagged corpora  that are essential for researchers working on various areas of NLP. Both linguists and computer scientists are members of the NLP group.

The group has several major long term research goals. These include:

• Developing Machine Translation (MT) systems between Tamil and other languages particularly English and Hindi
• Building lexical resources in Tamil that are essential for researchers and developers
• Developing basic tools for computational work in Tamil, such as morph analyzer, Part-Of-Speech (POS) tagger etc.
• Application of NLP tools for Information Extraction from domain specific texts so as to build Information Extraction systems for various domains such as medicine, agriculture etc.

The following is a gist of the achievements of the group in about two and half years since its inception in January 2000.

• The Tamil-Hindi Machine Aided Translation (MAT) system has a performance in the range of 75%
• The group has to its credit a Tamil search engine - the first of its kind for any Indian language
• The state-of-the-art Tamil Morphological analyser can handle nearly 3.5 million word forms including compound words with more than 95% accuracy
• A Tamil WordNet is being developed in collaboration with Dr. S Rajendran of Tamil University, Thanjavur
• A 15-day workshop on "Corpus-based Natural Language Processing" was conducted during Dec 2001
• The named entity extraction module is a part of Information extraction for medical literature