Synchronously Improving Multi-user English Translation Ability by Using AI

Abstract

English has become the most widely used language in the world. Everything we do in study, life and work is closely linked with English. With the continuous development of computer technology, machine translation is becoming more and more mature. The convergence of Artificial Intelligence (AI) and language learning is getting increasingly close, which brings great impact and challenge to the language education industry, but also provides an opportunity for the synchronous promotion of the development of the language education industry. With the further development of AI, machine translation can better meet the needs of most general translation, but in the face of professional, diversified, detailed and complex communication translation tasks containing human emotion, machine translation is still difficult to replace human translation. In order to improve the English translation ability of university students, this paper uses AI to propose the innovative factor based Quantum Particle Swarm Optimization-Convolutional Neural Network (QPSO-CNN) algorithm. Through the experiment, at first, the obtained dataset can ensure the accuracy and diversity of the collected results of English translation feature samples to the maximum extent, and the trained QPSO-CNN can be used to analyze the accuracy of the English translation ability of university students. Then, by comparing the convergence curve of QPSO-CNN and back propagation-CNN (BP-CNN), it is concluded that the proposed QPSO-CNN in this paper has been greatly improved in terms of model accuracy and convergence speed.