Welcome to the world of 'SabdasUtra'

About SabdasUtra         How are they useful
Polysemy is a major problem that one has to deal with while building bilingual lexical resources for the machine use. The concept of 'SabdasUtra' is an attempt to capture the underlying thread which relates various meanings in a polysymous word.      Both 'SabsasUtras' and 'lakshancharts' can be useful for any machine translation system. They are particularly useful for the 'anusAraka' system.
  
Voluntary Collaborative Activity      Interested in Word-Watching??
Building of SabdasUtras for English-Hindi is a voluntary collaborative effort. Language Technologies Research Centre(LTRC), International Institute of Information Technology, Hyderabad, is co-ordinating this activity.This is one of the three projects which were decided to be taken up for developing Lexical Resources for Indian Language (LERIL), at the "Workshop on Lexical Resources for Natural Language Processing", 5-8 Jan 2001, held at IIIT, Hyderabad. In the first phase the work will be done on a list of 5000 high frequency english words. Bilingual lexical resource of 'SabdasUtras' thus developed will be available under GPL.      Since it is a voluntary collaborative effort ALL are welcome to PARTICIPATE in the activity. SO if you like to think about WORDS and enjoy trying to connect the various meanings of a word you are welcome to join the activity of 'word-watching'.
If you want to join the activity please contact
dipti@iiit.net or vc@iiit.net
  
Minimum requirement to view the pages is to have an ISCII plugin.Please see Frequently asked Questions on ISCII plugin for more details. Click on any of the font /coding scheme below to view more information on SabdasUtra, Appendix and SabdasUtra for different words in that font / coding scheme. If you do not have the required fonts, click on the ITRANS or the ROMAN WX coding scheme.
ISCII
SHUSHA
ROMAN WX
ITRANS