Probabilistic combination of text classifiers using reliability indicators
- 11 August 2002
- proceedings article
- Published by Association for Computing Machinery (ACM)
- p. 207-214
- https://doi.org/10.1145/564376.564413
Abstract
The intuition that different text classifiers behave in qualitatively different ways has long motivated attempts to build a better metaclassifier via some combination of classifiers. We introduce a probabilistic method for combining classifiers that considers the context-sensitive reliabilities of contributing classifiers. The method harnesses reliability indicators---variables that provide a valuable signal about the performance of classifiers in different situations. We provide background, present procedures for building metaclassifiers that take into consideration both reliability indicators and classifier outputs, and review a set of comparative studies undertaken to evaluate the methodology.Keywords
This publication has 18 references indexed in Scilit:
- Combining multiple classifiers for text categorizationPublished by Association for Computing Machinery (ACM) ,2001
- A meta-learning approach for text categorizationPublished by Association for Computing Machinery (ACM) ,2001
- Hierarchical classification of Web contentPublished by Association for Computing Machinery (ACM) ,2000
- 10.1162/153244301753344614Applied Physics Letters, 2000
- Maximizing text-mining performanceIEEE Intelligent Systems and their Applications, 1999
- Inductive learning algorithms and representations for text categorizationPublished by Association for Computing Machinery (ACM) ,1998
- Classification of Text DocumentsThe Computer Journal, 1998
- A sequential algorithm for training text classifiersACM SIGIR Forum, 1995
- The effect multiple query representations on information retrieval system performancePublished by Association for Computing Machinery (ACM) ,1993
- Stacked generalizationNeural Networks, 1992