banglakit / lemmatizer

A rule-based lemmatizer for Bengali / Bangla based written in Python. Under active development.
23 stars 5 forks source link
bangla bengali lemmatization lemmatizer nlp

BanglaKit Lemmatizer

Build Badge

A rule-based lemmatizer for Bengali / Bangla based written in Python. Under active development.

Installation

The package is still not mature. We are not on PyPI yet, install from GitHub for the time being!

$ pip install git+https://github.com/banglakit/lemmatizer.git#egg=banglakit-lemmatizer

Usage


from banglakit import lemmatizer as lem
from banglakit.lemmatizer import BengaliLemmatizer

lemmatizer = BengaliLemmatizer()

lemmatizer.lemmatize('বাংলাদেশের', pos=lem.POS_PROPN)
# বাংলাদেশ

lemmatizer.lemmatize('বাংলাদেশের', pos='proper_noun')
# বাংলাদেশ