基于 TensorFlow & PaddlePaddle 的通用序列标注算法库（目前包含 BiLSTM+CRF, Stacked-BiLSTM+CRF 和 IDCNN+CRF，更多算法正在持续添加中）实现中文分词（Tokenizer / segmentation）、词性标注（Part Of Speech, POS）和命名实体识别（Named Entity Recognition, NER）等序列标注任务。

Extract city and country mentions from Text like GeoText without regex, but FlashText, a Aho-Corasick implementation.

Tool for slot extraction from text

Contains a Keras Bi-LSTM for Named Entity Recognition (This example demonstrates how you can use Kubeflow to train and deploy a Keras model with a custom prediction routine).