A study of different stemmer for Sindhi language based on Devanagari script
Sangita D. Makhija · International Conference on Computing for Sustainable Global Development · 2016
Presently on the globe, Internet plays a very important role in human's day to day life. On the blink of an eye, information must be retrieved by search engines. Web search engines are developing different techniques to make searching faster and retrieves information efficiently. Stemming is a technique to diminish word into its root word or stem word. It is also knows as a Conflation. Stemming is an important task which is included in Natural Language Processing (NLP) applications. This paper discusses various stemmers which are developed for different languages. Also, this research work aims to develop a stemmer for Devanagari script based Sindhi language. It strips the prefixes and suffixes from inflected word to their stem or root. This stemmer will minimize the problems of over and under stemming and retrieves the information efficiently and faster.