Rule-Based Derivational Stemmer for Sindhi Devanagari Using Suffix Stripping Approach

Abstract

Stemming is one of the important tasks of Natural Language Processing Applications, such as in Information retrieval and Machine Translation. In this research paper, we focused on Derivational Stemmer for resource-poor language Sindhi, in Devanagari Script by using suffix Stripping approach. A dictionary of frequent words is added to reduce over and under stemming error. This is our first attempt to develop a Rule-based Derivational Stemmer in Sindhi Devanagari Script. We compared the results of this derivational stemmer with inflectional stemmer of Sindhi Devanagari Script, previously developed by us.