The Role of WordNet in the Creation of a Trainable Message Understanding System

Abstract

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 efficiently create and customize, for his or her own application, an information extraction system with competitive precision and recall statistics. The use of 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 WordNet to minimize the effort on the end user for building the semantic knowledge bases and writing the regular patterns for new domains. Introduction and Background 1 The Message Understanding Conferences (MUCs) have given a great impetus to research in information extraction (IE). The systems which have participated in the MUCs have been quite successful...