Authors : Anjusha Pimpalshende and A.R. Mahajan
Abstract: Stemming is a process of extracting words from text and turning them into index terms in an IR system. Stemmers are based upon the written and not the spoken form of the language. Word stemming is one of the most significant factors that affect the performance of a Natural Language Processing (NLP) application such as Information Retrieval (IR) system, part of speech tagging, machine translation system and syntactic parsing, text summarization. A stemmer converts morphologically identical words to root word without performing analysis of that term. Sometimes, if we remove suffix from the word then the word may not be a proper Hindi word. So, to overcome this problem, a stemming algorithm is proposed that uses hybrid approach (combination of Brute force approach, suffix stripping approach and suffix substitution).
Anjusha Pimpalshende and A.R. Mahajan, 2018. Extraction of Root Words Using Morphological Analyzer for Hindi Text. International Journal of Soft Computing, 13: 134-138.