Chzhun Zhujyuj (Postgraduate student, National Research University Moscow Institute of Electronic Technology)
|
The article discusses the main methods of neurolinguistic training. Three stages of machine translation development are revealed: rule-based, statistical, neural learning. Two popular methods of neural machine translation are described: recurrent and convolutional. Advanced neural machine learning methods are characterized: ConvS2S, Transformer, RNMT +. A forecast was made for the further development of neural text translation systems.
Keywords:machine translation, neural learning, neural learning methods, neurolinguistics, ConvS2S, Transformer, RNMT +.
|
|
|
Read the full article …
|
Citation link: Chzhun Z. Overview of deep learning methods for neural machine translation // Современная наука: актуальные проблемы теории и практики. Серия: Естественные и Технические Науки. -2021. -№03. -С. 223-230 DOI 10.37882/2223-2966.2021.03.36 |
|
|