Pos Taging of Uzbek Text Using Hidden Markov Model

Boltayevich E. B., Samariddinovich S. S., Mirdjonovna K. S., Adali E., Yuldashevna X. Z.

8th International Conference on Computer Science and Engineering, UBMK 2023, Burdur, Turkey, 13 - 15 September 2023, pp.63-68 identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/ubmk59864.2023.10286619
  • City: Burdur
  • Country: Turkey
  • Page Numbers: pp.63-68
  • Keywords: emission probability, hidden Markov model, Hidden Markov Models, homonymy resolution, Markov chain, NLP, Parts of Speech Tagging, POS tagging, stochastic methods, transition probability, Viterbi algorithm, word groups
  • Istanbul Technical University Affiliated: Yes


Markov models are one of the most widely used machine learning methods for natural language processing. Markov chain and hidden Markov model is a stochastic (random) method used to model dynamic systems, and the current state of the system is predicted based on previous states. The Markov chain, which correctly generates a sequence of words in the generation of sentences, is widely used in NLP tasks. It is also used for identifying NERs in a sentence and POS tagging based on a hidden Markov model. Based on the Markov model, hidden tags are predicted based on the tagged words in the language corpus. This article presents methods and algorithms for automatic POS tagging of a given sentence based on the tagged Uzbek corpus using a hidden Markov model.