Project: Intelligent Information Extraction Student Researchers: Elena Eneva, Katharina Probst Advisors: Linda Bright Lankewicz Institution: University of the South (Sewanee) The project is a study of methods of automating the process of extracting information from text. We seek to show that compression methods for classification can be applied to the problem. Preliminary work classifying documents based upon compression has been promising. The topic will be pursued in a year-long study with experimentation. Automating the process of classifying text is an important task for mining data from the web. If robots can ascertain the type information contained on pages without human intervention and with high degree of accuracy, the search process can be improved.