Metadata-Version: 2.0
Name: russtress
Version: 0.1.2
Summary: Package that helps you to put lexical stress in russian text
Home-page: https://github.com/MashaPo/russtress
Author: Maria Ponomareva, Kirill Milintsevich
Author-email: ponomarevamawa@gmail.com
License: UNKNOWN
Keywords: nlp russian stress linguistic
Platform: UNKNOWN
Classifier: Development Status :: 4 - Beta
Classifier: Natural Language :: Russian
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Classifier: Topic :: Text Processing :: Linguistic
Classifier: Intended Audience :: Education
Requires-Dist: Keras
Requires-Dist: numpy
Requires-Dist: scipy
Requires-Dist: tensorflow

The tool based on LSTM predicts stress position in each word in russian text depending on the word context. 
For more details about the tool see `«Automated Word Stress Detection in Russian» <http://www.aclweb.org/anthology/W/W17/W17-4104.pdf>`_, EMNLP-2017, Copenhagen, Denmark.

Installation
============

Simple installation with pip

::

    pip install russtress

Usage example
========================

To put stress marks to your text

::

    >>> from russtress import Accent
    >>> accent = Accent()
    >>> text = 'Проставь, пожалуйста, ударения'
    >>> accented_text = accent.put_stress(text)
    >>> accented_text
    "Проста'вь, пожа'луйста, ударе'ния"

