Machine Translation Using Deep Learning : A Survey
Janhavi R. Chaudhary, Ankit C. Patel · Zenodo (CERN European Organization for Nuclear Research) · 2018
Machine Translation using Deep Learning (Neural Machine Translation) is a newly proposed approach to machine translation. The term Machine Translation is used in the sense of translation of one language to another, with no human improvement. It can also be referred to as automated translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to maximize the translation performance. This survey reveals the information about Deep Neural Network (DNN) and concept of deep learning in field of natural language processing i.e. machine translation. It is better to use Recurrent Neural Network(RNN) in Machine Translation. This paper studies various techniques used to train RNN for various language corpuses. RNN structure is very complicated and to train a large corpus is also a time-consuming task. Hence, a powerful hardware support (Graphics Processing Unit) is required. GPU improves the system performance by decreasing training time period.