Affiliation:
1. School of Foreign Languages, Changchun Institute of Technology , Changchun , Jilin , , China .
Abstract
Abstract
In this paper, after researching the natural language processing model, we use the knowledge representation technology to construct a knowledge base and use the sequence comparison algorithm to compare the sequences of Chinese and English translations, analyze the similarities and differences between the two sequences, and analyze the entropy of information between English and Chinese translations through the probabilistic theory and mathematical statistics method. On this basis, we analyze the differences between Chinese and English translations in terms of lexical dimension, syntactic dimension and articulation dimension and explore the differences in lexical richness and thematic concentration between Chinese and English based on “entropy”. The results show that Chinese is significantly higher than English translations in terms of language output length, sentence complexity, subordinate structure and phrase structure (p<0.001), and Chinese is significantly higher than English translations in terms of articulation (p<0.05). This paper provides an important reference value for studying the differences in stylistic features in Chinese-English translation.