Proceedings of the Fifth Message Understanding Conference, August 1993
GE-CMU: DESCRIPTION OF THE SHOGUN SYSTEM USED FOR MUC-5
Paul S. Jacobs, George Krupka, and Lisa Rau
Information Technology Laboratory
GE Research and Development
Schenectady, NY 12301 USA
Michael L. Mauldin, Teruko Mitamura, and Tsuyoshi Kitani
Center for Machine Translation
Carnegie Mellon University
Pittsburgh, PA 15213 USA
Ira Sider and Lois Childs
Management Data Systems
Martin Marietta
Philadelphia, PA 19101 USA
ABSTRACT
This paper describes the GE-CMU TIPSTER/SHOGUN system as configured for
the TIPSTER 24-month (MUC-5) benchmark, and gives details of the system's
performance on the selected Japanese and English texts. The SHOGUN
system is a distillation of some of the key ideas that emerged from
previous benchmarks and experiments, emphasizing a simple architecture
in which the focus is on detailed corpus-based knowledge. This design
allowed the project to meet its goal of achieving advances in coverage
and accuracy while showing consistently good performance across languages
and domains.
Full Paper
Last updated 05-Jan-95 by fuzzy@cmu.edu