Rule Based Urdu Stemmer

This paper presents Rule based Urdu Stemmer. In this technique rules are applied to remove suffix and prefix from the inflected words. Urdu is well spoken language all over the world but less work has been done on Urdu stemming. Stemmer helps us to find the root of the inflected word. Various possibilities of inflected words like ںو (vao+noon-gunna), ے (badi-ye), ںای (choti-ye+alif+noon-gunna) etc. have been identified and appropriate rules have been developed for them.