Home

Awesome

<!-- prettier-ignore-start --> <!-- markdownlint-disable --> <h1 align="center"> <a href='https://en.wikipedia.org/wiki/Mahmud_al-Kashgari'>Kashgari</a> </h1> <p align="center"> <a href="https://github.com/BrikerMan/kashgari/blob/master/LICENSE"> <img alt="GitHub" src="https://img.shields.io/github/license/BrikerMan/kashgari.svg?color=blue&style=popout"> </a> <a href="https://join.slack.com/t/kashgari/shared_invite/enQtODU4OTEzNDExNjUyLTY0MzI4MGFkZmRkY2VmMzdmZjRkZTYxMmMwNjMyOTI1NGE5YzQ2OTZkYzA1YWY0NTkyMDdlZGY5MGI5N2U4YzM"> <img alt="Slack" src="https://img.shields.io/badge/chat-Slack-blueviolet?logo=Slack&style=popout"> </a> <a href="https://travis-ci.com/BrikerMan/Kashgari"> <img src="https://travis-ci.com/BrikerMan/Kashgari.svg?branch=master"/> </a> <a href='https://coveralls.io/github/BrikerMan/Kashgari?branch=master'> <img src='https://coveralls.io/repos/github/BrikerMan/Kashgari/badge.svg?branch=master' alt='Coverage Status'/> </a> <a href="https://pepy.tech/project/kashgari"> <img src="https://pepy.tech/badge/kashgari"/> </a> <a href="https://pypi.org/project/kashgari/"> <img alt="PyPI" src="https://img.shields.io/pypi/v/kashgari.svg"> </a> </p> <h4 align="center"> <a href="#overview">Overview</a> | <a href="#performance">Performance</a> | <a href="#installation">Installation</a> | <a href="https://kashgari.readthedocs.io/">Documentation</a> | <a href="https://kashgari.readthedocs.io/about/contributing/">Contributing</a> </h4> <!-- markdownlint-enable --> <!-- prettier-ignore-end -->

🎉🎉🎉 We released the 2.0.0 version with TF2 Support. 🎉🎉🎉

If you use this project for your research, please cite:

@misc{Kashgari
  author = {Eliyar Eziz},
  title = {Kashgari},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/BrikerMan/Kashgari}}
}

Overview

Kashgari is a simple and powerful NLP Transfer learning framework, build a state-of-art model in 5 minutes for named entity recognition (NER), part-of-speech tagging (PoS), and text classification tasks.

Our Goal

Performance

Welcome to add performance report.

TaskLanguageDatasetScore
Named Entity RecognitionChinesePeople's Daily Ner Corpus95.57
Text ClassificationChineseSMP2018ECDTCorpus94.57

Installation

The project is based on Python 3.6+, because it is 2019 and type hinting is cool.

Backendkashgari versiondesc
TensorFlow 2.2+pip install 'kashgari>=2.0.2'TF2.10+ with tf.keras
TensorFlow 1.14+pip install 'kashgari>=1.0.0,<2.0.0'TF1.14+ with tf.keras
Keraspip install 'kashgari<1.0.0'keras version

You also need to install tensorflow_addons with TensorFlow.

TensorFlow Versiontensorflow_addons version
TensorFlow 2.1pip install tensorflow_addons==0.9.1
TensorFlow 2.2pip install tensorflow_addons==0.11.2
TensorFlow 2.3, 2.4, 2.5pip install tensorflow_addons==0.13.0

Tutorials

Here is a set of quick tutorials to get you started with the library:

There are also articles and posts that illustrate how to use Kashgari:

Examples:

Contributors ✨

Thanks goes to these wonderful people. And there are many ways to get involved. Start with the contributor guidelines and then check these open issues for specific tasks.