Tensorflow version of adapting transformer in paper "TENER: Adapting Transformer Encoder for Named Entity Recognition"
origin pytorch version: https://github.com/fastnlp/TENER origin TENER paper: https://arxiv.org/abs/1911.04474
Based on the original author's paper, we transplant the pytorch code of TENER to tensorflow platform, and getting similar performance to Bi-lstm in Chinese NER task.
The code is not rigorously tested, if you find a bug, welcome PR :D