Entity relationship extraction based on bi-channel neural network

It is of extremely important research value to identify the hidden relationship between the entities and extracted entities in this paper. Based on the two-channel convolutional neural network, the bi-directional long-short term memory network and multi-head attention mechanism have been added by this paper, and a relational extraction model of the two- channel neural network has been proposed. After the training of word vector, the resulting feature fusion is further classified, and finally the experimental verification is conducted on the SemEval-2010 Task 8 data set. The validation results have shown that this method has a good relationship extraction effect.