A Survey on Various Methods to Develop Morph Analyzer

A Morph Analyzer is a software tool which is used to detect morphemes from given sentence and provides grammatical analysis of each word present in the sentence. Morph analyzer is one of the essential tools for natural language processing and it is used for applications like machine translation. Lots of work has been reported in this field of morph analyzer for the foreign languages as well as some Indian languages. Previously for developing morph analyzer, both supervised and unsupervised methods had been tried. In this paper we compare various existing methods like Rule based Method, Suffix Stripping method, Finite state transducer approach and machine learning method. Then we also compare existing methods with respect to Gujarati language based on various parameters and check feasibility of implementing morph analyzer for Gujarati with each method.