Paper: HMM Specialization With Selective Lexicalization

ACL ID W99-0615
Title HMM Specialization With Selective Lexicalization
Venue 2000 Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora
Session Main Conference
Year 1999

We present a technique which complements Hidden Markov Models by incorporating some lexicalized states representing syntactically un- common words. 'Our approach examines the distribution of transitions, selects the uncom- mon 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.