Design of automatic recognition of modern Chinese metaphor types based on artificial intelligence technology

Inhalt:
Deep learning technology has been widely used in the field of artificial intelligence, great progress has been made in machine translation and man-machine dialogue. But there are still many problems in artificial intelligence’s “language understanding” of natural language, such as the recognition and translation of rhetoric in natural language, which is still a big problem. This paper combines linguistics with deep learning technology, we propose an approach to compare and recognize the different types of modern Chinese metaphor through using of the experimental design, according to data sampling method, and the experimental data model of CNN, RNN, Transform, Fast Text, Bert base. The study found that according to the characteristics of modern Chinese metaphor, the design is suitable and available for automatic recognition of metaphorical sentence types in modern Chinese, and the Bert base has the highest accuracy.