Machine translation is a sub-field of computational linguistics, and is about performing translation of text or speech from one language to another. Traditional machine translation systems typically rely on sophisticated feature engineering based on the statistical properties of text. Recently, deep learning has been used to solve this problem, with an approach known as Neural Machine Translation (NMT). An NMT system typically consists of two modules: an encoder and a decoder.
It first reads the source sentence using the encoder to build a thought vector: a sequence of numbers that represents the sentence's meaning. A decoder processes the sentence vector to emit a translation to other target ...
