STEMMING OF PUNJABI WORDS BY USING BRUTE FORCE TECHNIQUE

摘要

Stemming is an operation that conflates morphologically similar terms into a single term without doing complete morphological analysis. Stemming is used in information retrieval systems to improve performance. We describe a method to get the stem from the given word. Stemming is a technique which is required in information retrieval system and it is used to increase the performance of the retrieval result. All natural language processing systems must require a stemmer for it. The common goal of stemming is to standardize words by reducing a word to its base. Porter's stemmers have been used as a standard for English language. In this paper we have used Brute force technique with suffix stripping approach. Here we are using two approaches to get the maximum accuracy from the stemmer. For a language like Punjabi it is not easy to create a stemmer for it. Well known techniques for stemming are suffix removal, brute force technique, rule based technique and hybrid approaches. The need for good stemming algorithms for these languages has increased in the wake of search and retrieval system. In this we have created a huge database and a list of suffixes. With the help of big database we are getting higher accuracy than the other stemmers. We also reduce the over-stemming and understemming errors by finding number of words which causes these errors. We have already added these words in our database so to avoid the errors.