Stemming on basic words

SushilShrestha / NepaliStemmer

Snowball Nepali Stemmer Docker container.

MIT License

2 stars 0 forks source link

Stemming on basic words #1

Open oya163 opened 4 years ago

oya163 commented 4 years ago

There are issues in stemming common words. I tried the following.

>>> nepali_stemmer.stemWords(["झोले", "मण्डले", "एमाले", "काले", "अमेरिका", "काका"])
['झो', 'मण्ड', 'एमा', 'का', 'अमेरि', 'का']

SushilShrestha commented 4 years ago

Hi Oyesh, This repo wraps the snowball stemmer in a docker container for ease of use so actually I don't have total control over the stemming rules. A good place to checkout for the stemming rules might be the official snowball repo. (https://github.com/snowballstem/snowball)