Translation algorithm of English complex long sentences based on semantic features

Lei Wang,Shuai Jiang*,Pengpeng Li,Qing Li,Shuyun Guan
Department of Foreign Languages, Cangzhou Normal University, Cangzhou, 061001,China

Abstract:

Traditional English machine translation algorithms have low translation accuracy for English complex long sentences. To solve this problem, a translation processing algorithm for English complex long sentences based on semantic features is proposed. This algorithm analyzes the semantic hierarchy of phrases in complex English long sentences, uses context matrix to build semantic feature extraction model, and combines cosine similarity and weighted vector addition to obtain semantic matching and synthesis results, and recombines key phrases to complete the translation of complex English long sentences. The experimental results show that the algorithm designed in this paper has higher BLEU value, better phrase segmentation effect, shorter overall translation time, higher accuracy of translation results and lower recovery rate.