Kashgari

Overview | Performance | Installation | Documentation | Contributing

🎉🎉🎉 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.

• Human-friendly. Kashgari’s code is straightforward, well documented and tested, which makes it very easy to understand and modify.

• Powerful and simple. Kashgari allows you to apply state-of-the-art natural language processing (NLP) models to your text, such as named entity recognition (NER), part-of-speech tagging (PoS) and classification.

• Built-in transfer learning. Kashgari built-in pre-trained BERT and Word2vec embedding models, which makes it very simple to transfer learning to train your model.

• Fully scalable. Kashgari provides a simple, fast, and scalable environment for fast experimentation, train your models and experiment with new approaches using different embeddings and model structure.

• Production Ready. Kashgari could export model with SavedModel format for tensorflow serving, you could directly deploy it on the cloud.

Our Goal

• Academic users Easier experimentation to prove their hypothesis without coding from scratch.

• NLP beginners Learn how to build an NLP project with production level code quality.

• NLP developers Build a production level classification/labeling model within minutes.

Performance

Welcome to add performance report.

Task	Language	Dataset	Score
Named Entity Recognition	Chinese	People’s Daily Ner Corpus	95.57
Text Classification	Chinese	SMP2018ECDTCorpus	94.57

Installation

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

Backend	pypi version	desc
TensorFlow 2.1+	pip install 'kashgari>=2.0.0'	TF2.10+ with tf.keras
TensorFlow 1.14+	pip install 'kashgari>=1.0.0,<2.0.0'	TF1.14+ with tf.keras
Keras	pip install 'kashgari<1.0.0'	keras version

Tutorials

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

• Tutorial 1: Text Classification

• Tutorial 2: Text Labeling

• Tutorial 3: Seq2Seq

• Tutorial 4: Language Embedding

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

• 15 分钟搭建中文文本分类模型

• 基于 BERT 的中文命名实体识别（NER)

• BERT/ERNIE 文本分类和部署

• 五分钟搭建一个基于BERT的NER模型

• Multi-Class Text Classification with Kashgari in 15 minutes

Examples:

• Neural machine translation with Seq2Seq

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.

Overview

• Overview
• Our Goal
• Performance
• Installation
• Tutorials
• Contributors ✨

Tutorials

• Text Classification Model
  • Available Models
  • Train basic classification model
  • Text classification with transfer learning
  • Adjust model’s hyper-parameters
  • Use custom optimizer
  • Use callbacks
  • Multi-Label Classification
  • Customize your own model
  • Short Sentence Classification Performance
• Text Labeling Model
  • Available Models
  • Train basic NER model
  • Sequence labeling with transfer learning
  • Adjust model’s hyper-parameters
  • Use custom optimizer
  • Use callbacks
  • Customize your own model
  • Chinese NER Performance
• Seq2Seq Model
  • Train a translate model
  • Train with custom embedding

Embeddings

• Language Embeddings
  • Quick start
  • Feature Extract From Pre-trained Embedding
  • Classification and Labeling
  • Customized model
• Bare Embedding
• Word Embedding
• Bert Embedding
  • Example Usage - Text Classification
  • Use sentence pairs for input
• Transformer Embedding
  • Example Usage - Text Classification

Advanced Use Cases

• Tensorflow Serving

API

• Corpus
  • ChineseDailyNerCorpus
  • SMP2018ECDTCorpus
  • JigsawToxicCommentCorpus
• Embeddings
  • BareEmbedding
  • WordEmbedding
  • TransformerEmbedding
  • BertEmbedding
• Classification Models
  • Bidirectional LSTM Model
  • Bidirectional GRU Model
  • CNN Model
• Labeling Models
  • Bidirectional LSTM Model
  • Bidirectional GRU Model
  • Bidirectional LSTM CRF Model
  • Bidirectional GRU CRF Model
  • Bidirectional CNN LSTM Model
• Generators
  • CorpusGenerator
  • BatchDataSet
• Data Processors
  • SequenceProcessor
  • ClassificationProcessor

About

• Contributing & Support
  • Bug Reports
  • Reviewing Code
  • Answer Questions in Issues
  • Pull Requests
  • Documentation Improvements
• Release notes
  • Upgrading
  • Current Release
  • Legacy Version Changelog