Sanskrit lemmatizer for improvisation of morphological analyzer

Abstract

The process of stripping off affixes from a word to arrive at root word or lemma is known as Lemmatization. The usefulness of lemmatizer in natural language operations cannot be overlooked especially if the language is rich in its morphology. A lexicon cum rule based lemmatizer is built for Sanskrit Language. The Lemmatizer has profound applications in NLP main stream tasks like Information Retrieval, Morphological Analyzer ,POS taggers, Question-Answering Systems, Machine Translation Systems etc. Here the Sanskrit rule based morphological analyzer augmented with lemmatizer proved, analyzing Sanskrit word more precise and accurate to its morphological characteristics.

Keywords:

• Information Retrieval (IR)
• Natural Language Processing (NLP)
• Sanskrit
• Inflection
• Tokenization
• Morphology
• Lemma
• Case Markers (Vibhaktis)