By Topic

Research and implementation of part-of-speech tagging based on Hidden Markov Model

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
Zhang Youzhi ; Sch. of Comput. & Inf., Anqing Teachers'' Coll., Anqing, China

As separate problems of English, MA, POS, PDR can be considered independent with each other. In a practical research system, they are dependent, solution of the prior one forms the base for processing the next one. We Consider different features of these problems, after a comprehensive study, a divide-and-conqueror strategy is proposed and resolves them separately. First, a knowledge-based method is put forward for the solution of MA. The whole MA processing is completed by many subordinate functions dealing with different particular marks of English words. A strategy of combining the word length with statistic enumeration is developed to distinguish between the periods and abbreviations. Then, an approach combining Rule-based method with Hidden Markov Model (HMM) is put forward for POS tagging. Rule is introduced prior to the HMM approach not only to lower the time cost, but also to resolve the problems that cannot be solved with HMM. Solution to the POS tagging with this approach reports an accuracy of 99.83%.

Published in:

Computational Intelligence and Industrial Applications, 2009. PACIIA 2009. Asia-Pacific Conference on  (Volume:2 )

Date of Conference:

28-29 Nov. 2009