The explosion in the amount of free text materials on the Internet, and the use of this information by people from all walks of life, has made the issue of generalized information extraction a central one in Natural Language Processing. We have built a system that attempts to provide any user with the ability to e ciently create and customize, for his or her own application, an information extraction system with competitive precision and recall statistics. The use of a graphical user interface GUI, along with WordNet, in the design of the system helps take the computational linguist out of the process of customizing the system to each new domain. This is achieved by using the GUI to minimize the e ort on the end user for writing the regular patterns for new domains. WordNet acts as a domain independent semantic knowledge base.