PyCantonese: Cantonese Linguistics and NLP in Python

Full Documentation: https://pycantonese.org

PyCantonese is a Python library for Cantonese linguistics and natural language processing (NLP). Currently implemented features (more to come!):

• Accessing and searching corpus data
• Parsing and conversion tools for Jyutping romanization
• Parsing Cantonese text
• Stop words
• Word segmentation
• Part-of-speech tagging

Download and Install

To download and install the stable, most recent version:

$ pip install --upgrade pycantonese

Ready for more? Check out the Quickstart page.

Consulting

If your team would like professional assistance in using PyCantonese, freelance consulting and training services are available for both academic and commercial groups. Please email Jackson L. Lee.

Support

If you have found PyCantonese useful and would like to offer support, buying me a coffee would go a long way!

Links

• Source code: https://github.com/jacksonllee/pycantonese
• Bug tracker: https://github.com/jacksonllee/pycantonese/issues
• Social media: Facebook and Twitter

How to Cite

PyCantonese is authored and maintained by Jackson L. Lee.

Lee, Jackson L., Litong Chen, Charles Lam, Chaak Ming Lau, and Tsz-Him Tsui. 2022. PyCantonese: Cantonese Linguistics and NLP in Python. Proceedings of the 13th Language Resources and Evaluation Conference.

@inproceedings{lee-etal-2022-pycantonese,
   title = "PyCantonese: Cantonese Linguistics and NLP in Python",
   author = "Lee, Jackson L.  and
      Chen, Litong  and
      Lam, Charles  and
      Lau, Chaak Ming  and
      Tsui, Tsz-Him",
   booktitle = "Proceedings of The 13th Language Resources and Evaluation Conference",
   month = june,
   year = "2022",
   publisher = "European Language Resources Association",
   language = "English",
}

License

MIT License. Please see LICENSE.txt in the GitHub source code for details.

The HKCanCor dataset included in PyCantonese is substantially modified from its source in terms of format. The original dataset has a CC BY license. Please see pycantonese/data/hkcancor/README.md in the GitHub source code for details.

The rime-cantonese data (release 2021.05.16) is incorporated into PyCantonese for word segmentation and characters-to-Jyutping conversion. This data has a CC BY 4.0 license. Please see pycantonese/data/rime_cantonese/README.md in the GitHub source code for details.

Logo

The PyCantonese logo is the Chinese character 粵 meaning Cantonese, with artistic design by albino.snowman (Instagram handle).

Acknowledgments

Wonderful resources with a permissive license that have been incorporated into PyCantonese:

• HKCanCor
• rime-cantonese

Individuals who have contributed pull requests, bug reports, and other feedback (in alphabetical order of last names):

• @cathug
• Francis Bond
• Jenny Chim
• Eric Dong
• @g-traveller
• @graphemecluster
• Rachel Han
• Ryan Lai
• @laubonghaudoi
• Katrina Li
• Kevin Li
• @ZhanruiLiang
• Hill Ma
• @richielo
• @rylanchiu
• Stephan Stiller
• Robin Yuen

Changelog

Please see CHANGELOG.md.

Setting up a Development Environment

The latest code under development is available on GitHub at jacksonllee/pycantonese. To obtain this version for experimental features or for development:

$ git clone https://github.com/jacksonllee/pycantonese.git
$ cd pycantonese
$ pip install -e ".[dev]"

To run tests and styling checks:

$ pytest
$ flake8 src tests
$ black --check src tests

To build the documentation website files:

$ python docs/source/build_docs.py