English–Vietnamese Machine Translation Using Deep Learning for Chatbot Applications

Recently, artificial intelligence-based machine translation has been much improved over traditional methods. A machine translator is very useful for translating text or speech from one language to another. Machine translators have replaced the word mechanism in one language for words in another with verbatim translations. However, a good translation should be employed as both a sentence and a word that has a completed meaning in accordance with the context of the relevant sentence. In this paper, we studied English–Vietnamese translation using deep learning methods including recurrent neural network, long short-term memory, gated recurrent units, attention, and transformer. The deep learning-based machine translators were compared based on the test accuracy of the result translation. It was found that the best deep learning-based machine translator model was the Attention mechanism, and the Transformer yielded the second rank.