Learning Deep Semantics for Automatic Translation between Human Languages

The modern world relies increasingly on automatic translation of human languages to deal with billions of documents. Current translation systems struggle on complex texts and often produce misleading or incoherent outputs. Furthermore, they translate sentences independently and ignore their overall document-wide context. This project seeks to address these issues by devloping a new approach using semantics - the underlying meaning of the text - to drive translation; both as discrete structures and continuous representations learned via deep learning. This stands to improve translation quality, and lead international research and industry efforts in translation, thereby improving automatic tanslation for end-users.