HMM Specialization with Selective Lexicalization

Details HMM Specialization with Selective Lexicalization HMM Specialization with Selective Lexicalization

1999-12-23

arxiv.org/abs/cs/9912016v1

Proceedings of the 1999 Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora, pp

Computer Science

Computation and Language

7 pages, 6 figures

Scientific paper

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 performed 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.

Affiliated with

Also associated with

No associations

Rating

HMM Specialization with Selective Lexicalization does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with HMM Specialization with Selective Lexicalization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and HMM Specialization with Selective Lexicalization will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-504794