Publication Search Form

Keywords

Authors

Year

We found publication with these paramters.

Finite State Transducers Approximating Hidden Markov Models

Andre Kempe
This paper describes the conversion of a Hidden Markov Model into a sequential transducer that closely approximates the behavior of the stochastic model. This transformation is especially advantageous for part-of-speech tagging because the resulting transducer can be composed with other transducers that encode correction rules for the most frequent tagging errors. The speed of tagging is also improved. The described methods have been implemented and successfully tested on six languages.
Proc. ACL'97, Madrid, Spain, pp. 460-467
1997
1997/002

Attachments

mltt-97-02.pdf (188.05 kB)

mltt-97-02.ps.gz (52.25 kB)