ASIST AM 03 2003 START ConferenceManager    

Hybrid Hierarchical Classifiers for Categorization of Medical Documents

Miguel E. Ruiz Padmini Stinivasan

Presented at ASIST 2003 Annual Meeting -- Humanizing Information Technology: From Ideas to Bits and Back (ASIST AM 03 2003), Westin Long Beach, Long Beach, California, October 20 - 23, 2003


This article presents a study of the application of hierarchical classifiers based on the hierarchical mixtures of experts. In particular we present an extension of our work that explores the use of linear classifiers and a hybrid model that combines back propagation neural networks with linear classifiers. We test this model using the UMLS as the classification structure and a subset of medical abstracts from MEDLINE. Our results confirm that using the hierarchical structure of the classification vocabulary improves categorization performance.

Server START Conference Manager (V2.45.2)
Update Time 29 May 2003 at 07:31:04
Start Conference Manager
Conference Manager