Part of Speech Tagging Using a Network of Linear Separators

We present an architecture and an on-line learning algorithm and apply it to the problem of part-ofspeech tagging. The architecture presented, SNOW, is a network of linear separators in the feature space, utilizing the Winnow update algorithm. Multiplicative weight-update algorithms such as Winnow have been shown to have exceptionally good behavior when applied to very high dimensional problems, and especially when the target concepts depend on only a small subset of the features in the feature space. In this paper we describe an architecture that utilizes this mistake-driven algorithm for multi-class prediction - selecting the part of speech of a word. The experimental analysis presented here provides more evidence to that these algorithms are suitable for natural language problems. The algorithm used is an on-line algorithm: every example is used by the algorithm only once, and is then discarded. This has significance in terms of efficiency, as well as quick adaptation to new contex...

• Type: Conference
• Year: 1998
• Where: ACL
• Authors: Dan Roth, Dmitry Zelenko
• Keywords: ACL 1998, ACL 2007, Algorithms, On-line Learning Algorithm, Winnow Update Algorithm