## Computational Linguistics

September 2004, Vol. 30, No. 3, Pages 365-395
(doi: 10.1162/0891201041850876)
© 2004 Association for Computational Linguistics
Understanding the Yarowsky Algorithm
Article PDF (185.93 KB)
Abstract

Many problems in computational linguistics are well suited for bootstrapping (semisupervised learning) techniques. The Yarowsky algorithm is a well-known bootstrapping algorithm, but it is not mathematically well understood. This article analyzes it as optimizing an objective function. More specifically, a number of variants of the Yarowsky algorithm (though not the original algorithm itself) are shown to optimize either likelihood or a closely related objective function K.