UzbekLemmatizer

UzbekLemmatizer is a lemmatization library for word in the Uzbek language. It automatically reduces words to their canonical (dictionary) forms, which is essential for many NLP (Natural Language Processing) tasks.

Article: Development of a Rule-Based Lemmatization Algorithm Through Finite State Machine for Uzbek Language

GitHub link: https://github.com/MaksudSharipov/UzbekLemmatizer

For applications: maqsbek72@gmail.com

Features

• Lemmatizes Uzbek words to their root forms
• Supports basic rule-based lemmatization
• Simple and lightweight interface for easy integration

📌 Installation Note

To install UzbekLemmatizer, make sure you have an up-to-date version of pip and setuptools to avoid installation errors on newer Python versions (e.g. Python 3.12).

✅ Upgrade your build tools (recommended):

python -m pip install --upgrade pip setuptools wheel

✅ Then install the package:

pip install UzbekLemmatizer

Example 1:

import UzbekLemmatizer as ltz

print(ltz.Lemma('keladiganlarning'))

yoki

from UzbekLemmatizer import Lemma

print(Lemma('keladiganlarning'))

Result:

kel

Example 2:

import UzbekLemmatizer as ltz

print(ltz.Lemma('keladiganlarning', full=True))

yoki

from UzbekLemmatizer import Lemma

print(Lemma('keladiganlarning', full=True))

Result:

['keladiganlarning', 'kel', ['adigan', 'lar', 'ning'], [5, 5, 3]]