The project aims to develop a natural language toolkit for Nepali language. This toolkit will be used to process Nepali text and extract useful information from it.
There are a number of Nepali natural language toolkits available, but no standard single toolkit provides all the necessary functionalities for natural language processing (NLP).
Collect ready made resources for lemmatization, stemming, tokenization, and stopwords creation for Nepali language.
Test ready made tools and evaluate their performance.
Develop own models if the ready made tools are not satisfactory.
Integrate the developed models into the natural language toolkit.
Fundamentals of NLP