Probabilistic Context Free Grammar for Urdu

  • Neelam Mukhtar Department of Computer Science, University of Peshawar- Khyber Pukhtoon khawa, Pakistan
  • Mohammad Abid Khan Department of Computer Science, University of Peshawar- Khyber Pukhtoon khawa, Pakistan
  • Fatima TuzZuhra Department of Computer Science, University of Peshawar- Khyber Pukhtoon khawa, Pakistan
DOI: https://doi.org/10.32350/llr.22.04
Keywords: weights, efficiency, Perso-Arabic script, morphological system, parsing

Abstract

Abstract Views: 67

A Probabilistic Context Free Grammar (PCFG) for Urdu is developed from a Context Free Grammar (CFG) for sentences and phrases. Probabilities are assigned to the rules with addition of two new terms i.e. special weights and special probability. Weights are assigned to rules after performing certain calculations. Furthermore, if a rule has zero frequency at present but in future it is expected to be used, then instead of assigning zero probability a small value (0.0001 in our case) is assigned to it. All such rules are added like other rules to the Urdu PCFG. An Urdu PCFG is thus obtained.

Downloads

Download data is not yet available.
Published
2016-10-31
How to Cite
Neelam Mukhtar, Mohammad Abid Khan, & Fatima TuzZuhra. (2016). Probabilistic Context Free Grammar for Urdu. Linguistics and Literature Review, 2(2), 109-116. https://doi.org/10.32350/llr.22.04
Issue
Vol 2 No 2 (2016): Fall
Section
Articles

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution (CC-BY) 4.0 License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.