Neural network translation of Russian non-equivalent vocabulary into the Chinese language

The article is devoted to the study of the problem of translating Russian socio-political non-equivalent vocabulary found in modern electronic media and scientific works into Chinese, using neural network translation. The paper describes the translation methods used by the neural network, based on L.S. Barkhudarov’s classification. The success of the obtained results is stated. The purpose of this study is to determine the quality of neural network translation of non-equivalent vocabulary and to compare the results of artificial intelligence with manual translation. The material of the study is Russian non-equivalent vocabulary from socio-political discourse, selected from scientific articles and Internet media. The analysis has been carried out using neural network translation and comparative analy-sis. The study showed that in most cases the neural network successfully copes with the task, so it has the potential to become a new tool for practicing translators, but some of the translations offered to it can mislead native speakers, which highlights the need for further development in this area.