Building Morphological Analyzer for Nepali

Morphological analyzer is a fundamental tool in Natural Language Processing (NLP) that generates the morphological analyses of a given word-form. It can be used in enhancing the accuracy of POS-Tagging, Chunking, Syntactic Parsing, Word Sense Disambiguation (WSD), Information Retrieval (IR) Machine Translation (MT) Systems. This paper describes an ongoing effort to develop Nepali morphological analyzer, using an open source platform-Apertium (LT-Toolbox). Since, it is the initial stage of this project; we have confined our work to inflectional morphology. So far, we have covered all the possible categories, as per LDC-IL^1 POS tag-set of Nepali. Currently, the coverage of Nepali Morph-Analyzer is 20,000 words, classified into 219 paradigms.