Abstract

This paper presents a statistical model which trains from a corpus annotated with Part-OfSpeech tags and assigns them to previously unseen text with state-of-the-art accuracy(96.6%). The model can be classified as a Maximum Entropy model and simultaneously uses many contextual "features" to predict the POS tag. Furthermore, this paper demonstrates the use of specialized features to model difficult tagging decisions, discusses the corpus consistency problems discovered during the implementation of these features, and proposes a training strategy that mitigates these problems.

Citations

1654	B.: Building a large annotated corpus of english: The Penn treebank - Marcus, Marcinkiewicz, et al. - 1993
846	A Maximum Entropy Approach to Natural Language Processing - Berger, Pietra, et al. - 1996
540	Class-based n-gram models of natural language - Brown, Pietra, et al. - 1992
464	Inducing Features of Random Fields - Pietra, Pietra, et al. - 1997
355	Generalized Iterative Scaling for Log-Linear Models - Darroch, Ratcliff - 1972
287	Statistical Decision-Tree Models for Parsing - Magerman - 1995
227	Some advances in transformation-based part of speech tagging - Brill
212	Tagging English text with probabilistic model - Merialdo - 1994
114	A Maximum Entropy Model for Prepositional Phrase Attachment - Ratnaparkhi, Reynar, et al. - 1994
45	Decision Tree Parsing Using a Hidden Derivation Model - Jelinek - 1994
35	Adaptive language modeling using the maximum entropy principle.” Human Language Technology - Lau, Rosenfeld, et al. - 1993