Part-of-Speech Tagging with Two Sequential Transducers
We present a method of constructing and using a cascade consisting of
a left- and a right-sequential finite-state transducer (FST), T1 and
T2, for part-of-speech (POS) disambiguation. Compared to a Hidden
Markov model (HMM), this FST cascade has the advantage of significantly
higher processing speed, but at the cost of slightly lower accuracy.
Applications such as Information Retrieval, where the speed can be more
important than accuracy, could benefit from this approach.
S. Yu, A. Paun, eds., Proc. CIAA 2000, London, Ontario, Canada. Vol. 2088 of Lecture Notes in Computer Science, pp. 337-339, Springer-Verlag.