Silicon Republic article on DCU's Adapt centre's MT Evolution

Adapt LogoAdapt's Prof. Andy Way was recently interviewed by Silicon Republic on the MT evolution and it's application at the Adapt Centre, where Way and his team tackle language barriers that are “key challenges in enabling content to flow fluently across the globe”.

“From the late ’80s to about 2015, the dominant approach to MT was statistical (SMT). We needed large amounts of parallel data, ie source sentences and their human-provided translations, to build our statistical translation models, which essentially would suggest target-language words and phrases, which the model believed to be translations of the source sentence.

The last three years in MT have also seen neural MT (NMT) come to the fore. With NMT, all a research team needs is parallel data. The dominant model encodes the source sentence into a numerical vector representation, “which is in turn sent en bloc to the target-language decoder, whose job it is to generate the most likely target text from that vector”.

Way explained that NMT typically outperforms SMT and could be considered the “new state of the art”, citing more fluent translations and better word order as results. NMT does require much bigger training datasets, and models generally also take longer to train.

Full article: https://www.siliconrepublic.com/machines/machine-translation-adapt-dcu