๐๐๐ We are proud to announce that we entirely rewrote Kashgari with tf.keras, now Kashgari comes with easier to understand API and is faster! ๐๐๐
## 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
| Task | Language | Dataset | Score | Detail |
| ------------------------ | -------- | ------------------------- | -------------- | -------------------------------------------------------------------------------------------------------- |
| Named Entity Recognition | Chinese | People's Daily Ner Corpus | **94.46** (F1) | [Text Labeling Performance Report](https://kashgari.rtfd.io/tutorial/text-labeling.html#performance-report) |
## Tutorials
Here is a set of quick tutorials to get you started with the library:
- [Tutorial 1: Text Classification](./docs/tutorial/text-classification.md)
- [Tutorial 2: Text Labeling](./docs/tutorial/text-labeling.md)
- [Tutorial 3: Text Scoring](./docs/tutorial/text-scoring.md)
- [Tutorial 4: Language Embedding](./docs/embeddings/index.md)
There are also articles and posts that illustrate how to use Kashgari:
- [15 ๅ้ๆญๅปบไธญๆๆๆฌๅ็ฑปๆจกๅ](https://eliyar.biz/nlp_chinese_text_classification_in_15mins/)
- [ๅบไบ BERT ็ไธญๆๅฝๅๅฎไฝ่ฏๅซ๏ผNER)](https://eliyar.biz/nlp_chinese_bert_ner/)
- [BERT/ERNIE ๆๆฌๅ็ฑปๅ้จ็ฝฒ](https://eliyar.biz/nlp_train_and_deploy_bert_text_classification/)
- [ไบๅ้ๆญๅปบไธไธชๅบไบBERT็NERๆจกๅ](https://www.jianshu.com/p/1d6689851622)
- [Multi-Class Text Classification with Kashgari in 15 minutes](https://medium.com/@BrikerMan/multi-class-text-classification-with-kashgari-in-15mins-c3e744ce971d)
## Quick start
### Requirements and Installation
๐๐๐ We renamed again for consistency and clarity. From now on, it is all `kashgari`. ๐๐๐
The project is based on Python 3.6+, because it is 2019 and type hinting is cool.
| Backend | pypi version | desc |
| ---------------- | -------------------------------------- | --------------- |
| TensorFlow 2.x | `pip install 'kashgari>=2.0.0'` | coming soon |
| TensorFlow 1.14+ | `pip install 'kashgari>=1.0.0,<2.0.0'` | current version |
| Keras | `pip install 'kashgari<1.0.0'` | legacy version |
[Find more info about the name changing.](https://github.com/BrikerMan/Kashgari/releases/tag/v1.0.0)
### Example Usage
Let's run an NER labeling model with Bi\_LSTM Model.
```python
from kashgari.corpus import ChineseDailyNerCorpus
from kashgari.tasks.labeling import BiLSTM_Model
train_x, train_y = ChineseDailyNerCorpus.load_data('train')
test_x, test_y = ChineseDailyNerCorpus.load_data('test')
valid_x, valid_y = ChineseDailyNerCorpus.load_data('valid')
model = BiLSTM_Model()
model.fit(train_x, train_y, valid_x, valid_y, epochs=50)
"""
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input (InputLayer) (None, 97) 0
_________________________________________________________________
layer_embedding (Embedding) (None, 97, 100) 320600
_________________________________________________________________
layer_blstm (Bidirectional) (None, 97, 256) 235520
_________________________________________________________________
layer_dropout (Dropout) (None, 97, 256) 0
_________________________________________________________________
layer_time_distributed (Time (None, 97, 8) 2056
_________________________________________________________________
activation_7 (Activation) (None, 97, 8) 0
=================================================================
Total params: 558,176
Trainable params: 558,176
Non-trainable params: 0
_________________________________________________________________
Train on 20864 samples, validate on 2318 samples
Epoch 1/50
20864/20864 [==============================] - 9s 417us/sample - loss: 0.2508 - acc: 0.9333 - val_loss: 0.1240 - val_acc: 0.9607
"""
```
### Run with GPT-2 Embedding
```python
from kashgari.embeddings import GPT2Embedding
from kashgari.corpus import ChineseDailyNerCorpus
from kashgari.tasks.labeling import BiGRU_Model
train_x, train_y = ChineseDailyNerCorpus.load_data('train')
valid_x, valid_y = ChineseDailyNerCorpus.load_data('valid')
gpt2_embedding = GPT2Embedding('', sequence_length=30)
model = BiGRU_Model(gpt2_embedding)
model.fit(train_x, train_y, valid_x, valid_y, epochs=50)
```
### Run with Bert Embedding
```python
from kashgari.embeddings import BERTEmbedding
from kashgari.tasks.labeling import BiGRU_Model
from kashgari.corpus import ChineseDailyNerCorpus
bert_embedding = BERTEmbedding('', sequence_length=30)
model = BiGRU_Model(bert_embedding)
train_x, train_y = ChineseDailyNerCorpus.load_data()
model.fit(train_x, train_y)
```
## Sponsors
Support this project by becoming a sponsor. Your issues and feature request will be prioritized.[[Become a sponsor](https://www.patreon.com/join/brikerman?)]
## Contributors โจ
Thanks goes to these wonderful people. And there are many ways to get involved. Start with the [contributor guidelines](./docs/about/contributing.md) and then check these open issues for specific tasks.
Feel free to join the Slack group if you want to more involved in Kashgari's development.
[Slack Group Link](https://join.slack.com/t/kashgari/shared_invite/enQtODU4OTEzNDExNjUyLTY0MzI4MGFkZmRkY2VmMzdmZjRkZTYxMmMwNjMyOTI1NGE5YzQ2OTZkYzA1YWY0NTkyMDdlZGY5MGI5N2U4YzM)
## Reference
This library is inspired by and references following frameworks and papers.
- [flair - A very simple framework for state-of-the-art Natural Language Processing (NLP)](https://github.com/zalandoresearch/flair)
- [anago - Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging](https://github.com/Hironsan/anago)
- [Chinese-Word-Vectors](https://github.com/Embedding/Chinese-Word-Vectors)
- [bert4keras - Our light reimplement of bert for keras](https://github.com/bojone/bert4keras/)
