Quality Evaluation Model of Automatic Machine Translation based on Deep Learning Algorithm

With the continuous development of computer technology, machine translation methods have also experienced a long research process. In recent years, the research of artificial neural network has brought new solutions to machine translation. The application of sequence sequence model has made a qualitative leap in the performance of machine translation. The training of neural machine translation model depends on large-scale bilingual parallel data, which contains sufficient knowledge for machine learning. The training process is the process of data representation and knowledge extraction. How to use data enhancement methods to make model learning easier and knowledge extraction more sufficient is an important research topic. Automatic machine translation quality evaluation model based on deep learning algorithm is a method to evaluate the quality of automatic machine translation. This paper introduces the basic idea of qemt and some examples. We also give an example to illustrate how to use it to evaluate the quality of automatic machine translation. Qemt (quality evaluation model) is a method to evaluate the quality of automatic machine translation by comparing human translations generated by different natural language processing models such as part of speech markers or semantic similarity measures.