Title: Hierarchical neural network detection model based on deep context and attention mechanism

Authors: Yuxi Zhang; Yu Zhao

Addresses: Public Courses Department, Shaanxi Polytechnic Institute, Xianyang City, Shaanxi Province, 712000, China ' Public Courses Department, Shaanxi Polytechnic Institute, Xianyang City, Shaanxi Province, 712000, China

Abstract: In order to improve the ability of sentence event detection in natural language processing and solve the problem of event processing caused by polysemy, an event detection model based on neural network is proposed. The model adjusts the structure to a hierarchical neural network model based on neural network, and introduces attention calculation into the internal structure to realise the correlation analysis of sentence context. The value of the model is judged through performance analysis and application test. The results show that the average harmonic value of the model in polysemy detection is 74.1%, which is higher than the existing model. The application test shows that the model can detect events for sentences in different environments. The results show that the hierarchical neural network event detection model with deep contextual representation and attention mechanism has good performance, which provides theoretical support for the development of multi event detection technology.

Keywords: natural language processing; event detection; deep context; attention mechanism; hierarchical neural network.

DOI: 10.1504/IJCSM.2023.133634

International Journal of Computing Science and Mathematics, 2023 Vol.18 No.2, pp.162 - 175

Received: 14 Apr 2022
Accepted: 10 Feb 2023
Published online: 26 Sep 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article