Research on literary intelligent translation based on improved optimization model

Abstract

Machine translation is widely used in people’s daily life and production, occupying an important position. In order to improve the accuracy of literary intelligent translation, this study explores literary intelligent translation based on improved optimization model. According to semantic features, machine translation was used to create a semantic ontology optimization model that includes an encoder and a decoder, and a conversion layer including a forward neural network layer, a residual connection and a normalization layer were added to the semantic ontology optimization model between the encoder and the decoder, the conversion layer was used to achieve grammatical conversion, which improves the accuracy of intelligent translation of the semantic ontology optimization model. Results show that the BLEU value of using this method to translate literary sentences can reach 17.23 when the number of training steps is 8000, and the training time is low, the translation result has a low correlation misalignment rate, which can meet the user’s literary translation needs.