In this paper, four state-of-art probabilistic taggers . TnT tagger, TreeTagger, RF tagger and SVM tool, are applied to the Urdu language. For the purpose of the experiment, a syntactic tagset is proposed. A training corpus of 100,000 tokens is used to train the models. Using the lexicon extracted from the training corpus, SVM tool shows the best accuracy of . After providing a separate lexicon of 70,568 types, SVM tool again shows the best accuracy of .