HMM Specialization with Selective Lexicalization

Simple item page
dc.creatorKim, Jin-Dong
dc.creatorLee, Sang-Zoo
dc.creatorRim, Hae-Chang
dc.date1999-12-23
dc.date.accessioned2026-07-07T03:24:30Z
dc.date.available2026-07-07T03:24:30Z
dc.descriptionWe 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.
dc.description7 pages, 6 figures
dc.identifierhttps://arxiv.org/abs/cs/9912016
dc.identifierhttp://arxiv.org/abs/cs/9912016
dc.identifierProceedings of the 1999 Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora, pp.121-127, 1999
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/33347
dc.subjectComputation and Language
dc.subjectMachine Learning
dc.subjectI.2.6; I.2.7
dc.titleHMM Specialization with Selective Lexicalization
dc.typetext

Files

Collections

arXiv