Topic: Active information retrieval
By: T. Jaakkola (MIT), H. Siegelman (Technion)
Finding a few pieces of relevant information within a large dataset of predominantly incomplete and superficially similar information has become one of the pervasive challenges of information technology. We develop automated information retrieval methods with the ability to function accurately with minimal instruction of what is relevant, make use of information automatically queried from the user or environment at multiple levels of abstraction. Our active learning approach represents a paradigm shift from generally passive to interactive retrieval systems.
Questions and comments to the webmaster. This page is copyrighted by the Massachusetts Institute of Technology.