Research on Automatic Recognition of Metaphorical Sentence Types in Modern Chinese

Abstract

This paper presents work in progress towards automatic recognition of metaphorical sentence types in modern Chinese. We propose an approach to comparison recognition through the use of the experimental design, according to data sampling method, and the experimental data model of CNN, RNN, Transform, Fast Text, Bert base. Keeping in mind the characteristics of Chinese metaphorical sentence, the method is suitable and available for automatic recognition of metaphorical sentence types in modern Chinese, and the Bert base has the highest accuracy. This research contributes to Chinese natural language processing and can be applied in the fields of automatic composition correction, text classification, text summarization, automatic writing and so on. It is of great significance to Chinese text information and formal features, as well as the related process of human-computer communication.