Sciweavers

Share
CORR
1999
Springer

HMM Specialization with Selective Lexicalization

9 years 7 months ago
HMM Specialization with Selective Lexicalization
We present a technique which complements Hidden Markov Models by incorporating some lexicalized states representing syntactically uncommon words. 'Our approach examines the distribution of transitions, selects the uncommon words, and makes lexicalized states for the words. We perfor'med a part-of-speech tagging experiment on the Brown corpus to evaluate the resultant language model and discovered that this technique improved the tagging accuracy by 0.21% at the 95% level of confidence.
Jin-Dong Kim, Sang-Zoo Lee, Hae-Chang Rim
Added 22 Dec 2010
Updated 22 Dec 2010
Type Journal
Year 1999
Where CORR
Authors Jin-Dong Kim, Sang-Zoo Lee, Hae-Chang Rim
Comments (0)
books