Military Named Entity Recognition Based on Transfer Representation Learning
Weiping Liu, Zhang Bao, Weirong Chen, Zhang Cheng, Yuan Chen, Pan Renqian · 2020
In order to solve the shortage of annotated text in military field,a military named entity rec-ognition framework bi-directional encoder representations from transformers(BERT) bi-directional long short-term memory-conditional random field(Bi-LSTM-CRF)based on BERT,Bi-LSTM and CRF is proposed in combination with entity recognition technology. This framework takes the posi-tion,semantics block and part of speech as input features of the model. Though Transfer learning by BERT network,it grabs the general domain semantics coding features. Then,it decodes the military semantics features by Bi-LSTM. Finally,it realizes sequence prediction by CRF. The experimental results show that the named entity recognition framework performs better in accuracy,recall rate and F1 value than the current benchmark methods.