Neural Machine Translation: A Review

Felix Stahlberg
2020 The Journal of Artificial Intelligence Research  
The field of machine translation (MT), the automatic translation of written text from one natural language into another, has experienced a major paradigm shift in recent years. Statistical MT, which mainly relies on various count-based models and which used to dominate MT research for decades, has largely been superseded by neural machine translation (NMT), which tackles translation with a single neural network. In this work we will trace back the origins of modern NMT architectures to word and
more » ... ectures to word and sentence embeddings and earlier examples of the encoder-decoder network family. We will conclude with a short survey of more recent trends in the field.
doi:10.1613/jair.1.12007 fatcat:ryepzeon7nfnbgujk2kiacbrlm