Metadata-Version: 2.1
Name: uztagger
Version: 0.0.1
Summary: uztagger | Uzbek Morphological Part of Speech (POS) Tagging on Python
Home-page: https://github.com/UlugbekSalaev/uztagger
Author: Ulugbek Salaev
Author-email: ulugbek0302@gmail.com
License: UNKNOWN
Project-URL: Bug Tracker, https://github.com/UlugbekSalaev/uztagger/issues
Keywords: mophology,uzbek-language,tagging,pos,morphological tagging
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
License-File: LICENSE

# uztagger

https://pypi.org/project/uztagger <br>
https://github.com/UlugbekSalaev/uztagger

uztagger tool is focused to make tagging sentence with morphological Part of Speech (POS) tagset of Uzbek word based on morphemes. The tool includes list of POS tagset, tagging method. 
It is created as a python library and uploaded to [PyPI](https://pypi.org/). It is simply easy to use in your python project or other programming language projects via the API. 

## About project
The tool is focused to make tagging sentence with morphological Part of Speech (POS) tagset of Uzbek word based on morphemes. The tool includes list of POS tagset, tagging method.

## Quick links

- [Github](https://github.com/UlugbekSalaev/uztagger)
- [PyPI](https://pypi.org/project/uztagger/)
- [Web-UI](https://nlp.urdu.uz/?menu=uztagger)

## Demo

You can use [web interface](http://nlp.urdu.uz/?menu=uztagger).

## Features

- Tagging 
- POS tag list
- Help function

## Usage

Three options to run uztagger:

- pip
- API 
- Web interface

### pip installation

To install uztagger, simply run:

```code
pip install uztagger
```

After installation, use in python like following:
```yml
# import the library
from uztagger import Tagger
# create an object 
tagger = Tagger()
# call tagging method
tagger.predict_pos('Bizlar bugun maktabga bormoqchimiz.')
```

### API
API configurations: 
 - Method: GET
 - Response type: <code>string</code>


 - URL: https://uzbeknlp.herokuapp.com/uztagger
   - Parameters: <code>sentence:string</code></code>
   - Sample Request: https://uzbeknlp.herokuapp.com/uztagger?sentence=maktabimda

### Web-UI

The web interface created to use easily the library:
You can use web interface [here](http://nlp.urdu.uz/?menu=uztagger).

![Demo image](./docs/images/web-interface-ui.png)

### Options
When you use PyPI or API, you should use following options as POS tag of a word which is optional parameters of `lemmatize()` and `analyze()` metods:<br>
    `NOUN`  Noun<br>
    `VERB`  Verb<br>
    `ADJ`   Adjective<br>
    `NUM`   Numerical<br>
    `PRN`   Pronoun<br>
    `ADV`   Adverb

### Result Explaining

The method ```predict_pos``` returns list of sentences in a string type, that an item of the list contain tuples for each token of the sentence with following format: ```(token, pos)```, for POS tag list, see <i>POS Tag List</i> section on below.  
#### Result from `tagger` method

## Documentation

See [here](https://github.com/UlugbekSalaev/uztagger).

## Citation

```tex
@misc{uztagger,
  title={{uztagger}: Morphological Part of Speech Tagger Tool for Uzbek},
  url={https://github.com/UlugbekSalaev/uztagger},
  note={Software available from https://github.com/UlugbekSalaev/uztagger},
  author={
    Ulugbek Salaev},
  year={2022},
}
```

## Contact

For help and feedback, please feel free to contact [the author](https://github.com/UlugbekSalaev).

