Rule Based Gujarati Morphological Analyzer
Gujarati is an Indian Language spoken widely by over 50 million people of Gujarat in India and abroad. Gujarati like other Indo-Aryan languages like Hindi, Marathi is morphologically rich. Morphological analysis is an important step for many Natural Language Preprocessing (NLP) applications like machine translation, grammar inference, and information retrieval etc. In this paper we have presented morphological analyzer on rule based approach. Lexical dictionary of root words is created. Manually crafted rules with linguist are developed. The analyzer tool takes Gujarati sentence as an input, and produces its grammar class, gender, number, and tense and person information with its root words. The tool works on both inflectional and derivational morphemes. We have obtained accuracy of 87.48% upon evaluation with text taken from essays and short stories.
Keywords: Gujarati, Morphological Analyzer, Rule based, Natural language Processing, Part of Speech Tagging
ABOUT THE AUTHORS
U. N. Kapadia received B.E. and M.C.A degrees from Veer Narmad South Gujarat University. He also has cleared State Level eligibility test (SET), a qualifying exam. He has worked as System Engineer in TCS. He has worked as Assistant Professor at the department and researcher in the area of Natural Language Processing.
A. A. Desai, completed his graduation and post graduation from Veer Narmad South Gujarat University. He earned his Ph.D. in the year 1997 in the field of Operation Research and Computer Science. He is a Dean of faculty of Computer Science and Information Technology and Chairman Board of Studies. He is and Editor in Chief of VNSGU Journal of Science and Technology and also serving as a member of Editorial board for some of the national and international journals. He has more than 50 research papers and four books to his credit.
IJCSI Published Papers Indexed By: