SEMANTIC ROLE ANALYSIS METHOD, READABLE STORAGE MEDIUM, TERMINAL DEVICE AND APPARATUS

摘要

The present application belongs to the technical field of computers, and relates in particular to a semantic role analysis method, a computer-readable storage medium, a terminal device and an apparatus. The method comprises: in the process of part-of-speech analysis, one neural network model is used for forward part-of-speech analysis, and another neural network model is used for reverse part-of-speech analysis. In the process of semantic role analysis, one neural network model is used for forward semantic role analysis, and another neural network model is used for reverse semantic role analysis. Thus, an originally complex neural network model is divided into relatively simple neural network models, and then the output of each neural network model is comprehensively processed to obtain a result. Due to the simplification of the neural network model structure, the computational load is greatly reduced and the analysis efficiency is improved.