Nepali Stemmer

This is a simple Nepali stemmer. It iteratively separates out the suffixes (postpositions) until no more separation can be processed. The algorithm is based on hindi-stemmer.

Features:

• Iterative separation
• Handles the postposition attached with punctuations carefully
  • Example: नेपाललाई, -> नेपाल लाई,
• Basic text cleaning
• Cross-verification with Nepali dictionary

How to run

>>> from nepali_stemmer.stemmer import NepStemmer
>>> nepstem = NepStemmer()
>>> nepstem.stem("नेपालको एमाले पार्टीका झोले, मण्डलेहरु अमेरिका आउने रे !")                                                                                                      

'नेपाल को एमाले पार्टी का झोले, मण्डले हरु अमेरिका आउने रे !'

To-do:

• Word transformation with stemming process
• IR evaluation
• Code-mixed data

References:

• Suffix list: https://github.com/birat-bade/NepaliStemmer
• Nepali Dictionary : https://github.com/PraveshKoirala/stemmer
• Algorithm : https://github.com/sainimohit23/hindi-stemmer

Contact

Email: oyashi

Note: Project created during COVID-19 quarantine out-of-boredom and necessity