Differential Analysis of Stylistic Features in English Translation Teaching Based on Semantic Contrastive Analysis

Abstract

In this paper, in the process of digitization of stylistic features in English translation teaching, the simulated stylistic features in English translation teaching activities are quantified and pre-emphasized to obtain the decoder of stylistic features of English translation with higher precision, and the stylistic features recognition algorithm in English translation teaching is designed, and the results of the stylistic features recognition in English translation teaching can be obtained by substituting the initial data into the recognition algorithm. Based on stylistic feature recognition, combined with the post-particle swarm optimization algorithm and artificial neural network to construct the stylistic feature analysis model in English translation teaching, and use the method of statistical analysis to analyze the differences of stylistic features in English translation teaching. The results show that the rank means value of auxiliary is the highest, reaching 209.81, the lowest is a preposition (145.17), and the conjunction and adverb are 154.17 and 157.45 respectively, which indicates that auxiliary has the strongest variability of features in the translation of English novels, and this study enables students to have a comprehensive and in-depth understanding of the text, to grasp the stylistic features of the text, and to improve the students’ comprehensive English language ability and translation level.

Keywords

• particle swarm optimization algorithm
• artificial neural network
• decoder
• variability analysis
• english translation teaching
• 00a73