An Inquiry into the Translation of English Literary Metaphors Based on Text Mining Techniques

Abstract

In this paper, the vector space model is used to convert the English literature text to be processed into a feature vector composed of feature items, and after adding weights to the feature items, it is composed into an N -dimensional space. After calculating the text similarity using the vector angle cosine, the knowledge base of English literature metaphors and an automatic recognition model are constructed by combining them with a Bayesian classification algorithm. Starting from the research purpose, we determine the research object and tools and analyze an example of English literary metaphor translation through the combination of simulation analysis and statistical analysis. The results show that the running speed of NBC is 10.2% faster than that of CFC, the speed of SOFMC is 70.1% faster than that of CFC, the accuracy rate of NBC is 32.8% higher than that of SOFMC, and that of CFC is 41.8% higher than that of SOFMC, and in terms of the combined running speed and accuracy rate, NBC performs better than SOFMC and CFC, i.e., it shows that the Bayesian classification algorithm is useful for dealing with English metaphor recognition and Chinese translation with excellent performance. In terms of lexical translation accuracy, the translated English literary metaphor texts with labeled lexical categories are significantly higher than the translated English literary metaphor texts without labeled lexical categories, with a difference value of 6.31%. This study extends the scope of cognitive linguistics research and offers a guiding reference value for translating English literary metaphors.