Annual Report Homepage   Previous Next
SMA Logo & Rationale
Front Cover Design
Vision & Mission
Committee Members & Directors
Programme Co-Chairs
Particpation by Industry & NRIs
Job Placement
Faculty & Staff
Students & Alumni
  Research Fellows And Research Projects  
  Project abstracts can be viewed from the CD-ROM which is enclosed or the SMA website (  
  AMM&NS Programme HPCES Programme IMST Programme MEBCS Programme  
  CS Programme        
  CS Programme  
Expertise: Natural language processing - information retrieval and word sense disambiguous
Semi-Supervised Learning for Wide Coverage Word Sense Disambiguation
Project Advisor
Assoc Prof Lee Wee Sun
Duration :
March 2004 to March 2005

Project Abstract:

Word sense disambiguation refers to the task of determining the correct meaning of a word in context. For example, the word “plant” has multiple meanings including “factory” and “flora” depending on the context in which it is used. Word sense disambiguation can generally be done well by learning machines that have been trained using supervised learning methods.

Unfortunately, to train a word sense disambiguation model with a coverage of about 3000 words using a standard supervised learning method would require an estimated 16 man-years of human annotation effort. This project explores the possibility of reducing the amount of human annotation required for word sense disambiguation through the use of semi-supervised machine learning methods that reduce the need for human annotation by exploiting the large amount of unannotated documents that are easily available.

  - Go back to titles  
Back to Top   Previous Next