Skip to content

Comparison of Chinese Named Entity Recognition Models between NeuroNER and BertNER

Notifications You must be signed in to change notification settings

rct-ai/rct-NER-Chinese

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 

Repository files navigation

NER-Chinese

Comparison of Chinese Named Entity Recognition Models between NeuroNER and BertNER

  1. Word Embedding-BiLSTM-CRF:众多实验表明,该结构属于命名实体识别中最主流的模型,代表的工具有:NeuroNER。它主要由Embedding层(主要有词向量,字向量以及一些额外特征)、双向LSTM层、以及最后的CRF层构成。
  2. Bert-BiLSTM-CRF:随着Bert语言模型在NLP领域横扫了11项任务的最优结果,将其在中文命名实体识别中Fine-tune必然成为趋势。它主要是使用bert模型替换了原来网络的word2vec部分,从而构成Embedding层,同样使用双向LSTM层以及最后的CRF层来完成序列预测。

About

Comparison of Chinese Named Entity Recognition Models between NeuroNER and BertNER

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 95.5%
  • Perl 4.5%