UzbekTagger 1.1.1

Part of Speech Tagger for Uzbek Language.

UzbekTagger

UzbekTagger is a part-of-speech (POS) tagging library for text in the Uzbek language. This library allows you to automatically assign grammatical categories (such as noun, verb, adjective, etc.) to each word in a given text.

Article: UzbekTagger: The rule-based POS tagger for Uzbek language

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

Note: We highly recommend checking out our modern, highly accurate Transformer-based POS tagger: UzbekTaggerBERT v0.1.2!

Features

• Tokenizes and tags Uzbek sentences with grammatical categories
• Supports basic POS tagging (NOUN, VERB, ADJ, PRON, etc.)
• Simple and lightweight interface

Installation:

You can install the library using pip:

pip install UzbekTagger

Example:

from UzbekTagger import pos

print(pos.tagger("Men bugun uyga ertaroq ketdim. Boshqa bolalar bugun maktabdan kechroq kelar ekan."))

Result:

 Men/PRON bugun/ADV uyga/NOUN ertaroq/ADV ketdim/VERB ./PUNCT

 Boshqa/ADV bolalar/NOUN bugun/ADV maktabdan/NOUN kechroq/VERB kelar ekan/VERB ./PUNCT