Center for Language Engineering

 
 



 

 

KICS
KICS-UET


 
 

[ Localization ] [ Language Processing ] [ Linguistic Resources ]

 
   
  Urdu Stemmer  
     
  Introduction  
 

Stemming is the process of extracting stem (base word) from the given word. This base word needs not to be in the root (meaningful) form. A word can be a combination of affixes and stem. An affix can be a prefix, postfix or infix. In the developed Urdu Stemmer Assas-band, foreign words are not handled. The task of Urdu Stemmer is to extract stem, prefix and postfix from the given word. Assas-band only returns meaningful form of the stem which means that the base form is converted into root by attaching required character(s). Assas-band distinguishes between stem of masculine and feminine forms. For example the stem of لڑکیاں (girls) is لڑکی (girl), whereas the stem of لڑکوں (boys) is لڑکا (boy).

 
   
  Online Urdu Stemmer  
  Enter the word against the ان پٹ لفظ option. Then by pressing Enter key or clicking on the لفظی راس کاری کریں button, following information will be shown. If there will be any prefix in the word then it will be shown against the سابقہ heading. The stem is shown in the راس pane and postfix if exists is shown in the لاحقہ pane.  
     
  Urdu Stemmer, Assas-band Utility v1.0 License  
     
  This page has been accessed: times, since 23 August 2011  
 

webmaster@cle.org.pk