Skip to main content

Linguistica 5: Unsupervised Learning of Linguistic Structure

Project description

https://travis-ci.org/linguistica-uchicago/lxa5.svg?branch=master https://coveralls.io/repos/github/linguistica-uchicago/lxa5/badge.svg?branch=master Code Health

Linguistica 5 is a Python library for unsupervised learning of linguistic structure, based on Goldsmith (2001, 2006) and all subsequent developments.

Full documentation: http://linguistica-uchicago.github.io/lxa5/

Apart from being a Python library, Linguistica 5 provides two additional interfaces: (i) graphical user interface; (ii) command line interface.

Work by Jackson Lee and John Goldsmith

Download and install

Linguistica 5 is available through pip:

$ pip install linguistica

Linguistica 5 requires Python 3.4 or above. Core dependencies are NumPy, SciPy, and NetworkX. If you encounter issues in installing these dependencies, consider using the Python distribution Anaconda (or Miniconda) with these dependencies installed.

To use the graphical user interface, PyQt5 and SIP are required. PyQt5 is readily available from pip:

$ pip install PyQt5

At the time of writing (March 2017), SIP is best downloaded and installed from its source. (SIP is available through pip, but it does not include the C/C++ code generator for PyQt5.)

Using Linguistica 5

To use Linguistica 5 as a Python library, simply import linguistica in your Python programs:

import linguistica as lxa

Quick library demo here.

To launch the Linguistica 5 graphical user interface (with SIP and PyQt5 installed):

$ python -m linguistica gui

To launch the Linguistica 5 command line interface:

$ python -m linguistica cli

Citation

If you use Linguistica 5, please cite this paper:

@InProceedings{lee-goldsmith:2016:lxa5,
  author    = {Lee, Jackson L. and Goldsmith, John A.},
  title     = {Linguistica 5: Unsupervised Learning of Linguistic Structure},
  booktitle = {Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics},
  month     = {June},
  year      = {2016},
  address   = {San Diego, California},
  publisher = {Association for Computational Linguistics},
  pages     = {22--26},
  url       = {http://www.aclweb.org/anthology/N16-3005}
}

Source code

The source code of Linguistica 5 is officially released on PyPI: https://pypi.python.org/pypi/linguistica

It is also hosted on GitHub, possibly with work in progress: https://github.com/linguistica-uchicago/lxa5

Technical support

Please open issues for questions and bug reports. Alternatively, please feel free to contact Jackson Lee and John Goldsmith.

License

MIT License

See LICENSE.txt on the GitHub repository.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

linguistica-5.1.1.tar.gz (3.6 MB view hashes)

Uploaded Source

Built Distribution

linguistica-5.1.1-py3-none-any.whl (3.6 MB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page