To solve the problems that a large amount of annotated corpus is required for entity recognition model training in military domain and the lack of open source corpus data,this paper proposes a training method for entity recognition model of military logistics requirements that integrates active learning and deep learning.By incorporating active learning methods with different sample selection strategies into BERT-BiL-STM-CRF model training,the generalization ability of the military logistics demand entity recognition model is rapidly improved by screening valuable training samples,and the number of sample annotations is also re-duced to achieve a small amount of annotated corpus to train the model.Experiments show that the uncer-tainty and diversity sample selection strategies reduce the expert annotation by 56.25％and 62.5％,re-spectively,under the premise of guaranteeing the model performance,effectively reducing the sample size required for model training,which is important for the demand entity recognition task in the military logis-tics domain where the corpus is lacking.
关键词
军事物流/BERT/实体识别/主动学习/深度学习
Key words
military logistics/BERT/entity recognition/active learning/deep learning
维普
万方数据