A Military Named Entity Relation Extraction Approach Based on Deep Learning
Xuefeng Wang, Ruopeng Yang, Yulong Feng, Dongsheng Li, Jianfeng Hou · 2018
The critical information of the commander is drowned in the massive battlefield messages, and extracting the structured combat data from the unstructured battlefield message is of great significance for assisting the commander's decision-making. The relation between military named entities is the basis of military intelligence analysis, and it is important for acquiring the combat compilation, deployment location, target status, command relationship of both sides. In view of the problems of insufficient artificial construction features, inaccurate Chinese word segmentation in the military field and insufficient correlation between input and output in the current military named entity relation extraction, the author proposes a relation extraction method based on deep learning. Combining Bi-directional Long Short-Term Memory (Bi-LSTM) neural network's ability to remember long sentence context, the ability of character embedding to express Chinese characters and the ability of attention mechanism to learn the correlation between input and output, the Character+Bi-LSTM+ Attention entity relation extraction model was constructed. In order to verify the validity of the method, experiments were carried out on the military scenario corpus, and the experimental results show that the extraction effect of the method is further improved than the traditional method.