![Sample our Mathematics & Statistics journals, sign in here to start your FREE access for 14 days]({"type":"image" , "src" : "/sda/5943/TOC-Subject-Sample-2021-Mathematics-Statistics.jpg"})
Abstract
The Study of word formation is called as morphology. Morphological analysis is one of the important tasks of Natural Language Processing. IR and Machine Translation are two important applications of Morphological Analyzer. In order to search or retrieve any information from web we need, normalize form of a word .This task is accomplish by two morphological analyzer Stemmer and Lemmatizer . Stemming is a simple process of strip off the word endings to get the normalized form of a word, called stem. The process of stemming suffers from two types of errors i.e. over stemming and under stemming. We can handle Under stemming by making a database of exceptional words whereas Over stemming is handle by lemmatizer .Lemma is correct root word or dictionary word generated by applying some rules for affix removal and some additional rules for making a correct dictionary word. This paper presents design and development of lemmatizer for Sindhi language in Devnagri script. This is our first attempt to develop a lemmatizer for Sindhi language in devanagri script.