Metadata-Version: 2.1
Name: estnltk_neural
Version: 1.7.1
Summary: EstNLTK neural -- EstNLTK's linguistic analysis based on neural models
Home-page: https://github.com/estnltk/estnltk
Author: University of Tartu
Author-email: siim.orasmaa@gmail.com, alex.tk.fb@gmail.com, tpetmanson@gmail.com, swen@math.ut.ee
License: GPLv2
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Science/Research
Classifier: Intended Audience :: Information Technology
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Classifier: Topic :: Text Processing
Classifier: Topic :: Text Processing :: Linguistic
Description-Content-Type: text/markdown
License-File: LICENSE

EstNLTK neural -- EstNLTK's linguistic analysis based on neural models
===========================================================================

This package contains EstNLTK's linguistic analysis tools that use neural models:

* neural morphological tagger (disambiguator);
* bert embeddings tagger;
* stanza syntax tagger and stanza ensemble syntax tagger;

Note: these tools require installation of deep learning frameworks (`tensorflow`, `pytorch`), and are demanding for computational resources; they also rely on large models which need to be downloaded separately. 

The EstNLTK project is funded by EKT ([Eesti Keeletehnoloogia Riiklik Programm](https://www.keeletehnoloogia.ee/)).

### Installation

EstNLTK-neural is available as a PyPI wheel:  

```
pip install estnltk_neural
```

And as an Anaconda package:

```
conda install -c estnltk -c conda-forge estnltk_neural
```

Supported Python versions: 3.7+

### Neural models

Models required by neural tools are large, and therefore cannot be distributed with this package. 
However, our tagger classes are implemented in a way that once you create an instance of a neural tagger, you'll be asked  for a permission to download missing models, and if you give the permission, the model will be downloaded (and installed in a proper location) automatically. 
If needed, you can also change the default location where downloaded models will be placed, see [this tutorial](https://github.com/estnltk/estnltk/blob/bebfa8c2dc7ce54370d1b961cc0a0615b8ae5c85/tutorials/basics/estnltk_resources.ipynb) for details.

### Documentation

EstNLTK's [NLP component tutorials](https://github.com/estnltk/estnltk/tree/main/tutorials/nlp_pipeline) also cover information about neural taggers. 

### Source

The source of the last release is available at the [main branch](https://github.com/estnltk/estnltk/tree/main/estnltk_neural).

---

License: GNU General Public License v2.0

(C) University of Tartu  
