Information retrieval / text mining

I am a member of the Texterra project aimed at providing a framework for analysing unstructured texts using knowledge derived from hyperlinked encyclopedias, in particular, Wikipedia.

Activities:

• Computing similarity between objects, in particular, SimRank computation
• Word sense disambiguation
• Keyphrases extraction from text using Wikipedia as the controlled vocabulary
• Graph analysis for linked encyclopedic terms.
  Community Hierarchy of the Wikipedia Graph

Back to main page

This document was translated from L^AT_EX by H^EV^EA.