Multi-level inflection handling stemmer using iterative suffix-stripping for Malayalam language

Stemming is the process of extracting a stem or root word from an inflected word. Corpus based methods for stemming that involves maintaining a corpus with all inflected forms of all words is not practical for Dravidian languages like Malayalam that have a high degree of inflection. This paper proposes a rule based stemmer that uses iterative suffix stripping method. Using a root word corpus that is relatively smaller in size, the proposed method presents an increased efficiency and reduced complexity. It is able to handle multiple levels of inflection that can occur to a word, by following an iterative suffix stripping methodology.