This paper applies error-correcting output coding
(ECOC) to the task of document categorization.
ECOC, of recent vintage in the
AI literature, is a method for decomposing a
multiway classication problem into many binary
classication tasks, and then combining
the results of the subtasks into a hypothesized
solution to the original problem. There has
been much recent interest in the machine learning
community about algorithms which integrate
advice" from many subordinate predictors
into a single classier, and error-correcting
output coding is one such technique. We provide
experimental results on several real-world
datasets, extracted from the Internet, which
demonstrate that ECOC can oer signicant
improvements in accuracy over conventional
classication algorithms.