Knowledge Distillation for Sustainable Neural Machine Translation

no code implementations • AMTA 2022 • Wandri Jooste, Andy Way, Rejwanul Haque, Riccardo Superbo

Knowledge distillation (KD) can be used to reduce model size and training time, without significant loss in performance.

Knowledge Distillation Machine Translation +1

The ADAPT Centre’s Neural MT Systems for the WAT 2020 Document-Level Translation Task

no code implementations • AACL (WAT) 2020 • Wandri Jooste, Rejwanul Haque, Andy Way

In this paper we describe the ADAPT Centre’s submissions to the WAT 2020 document-level Business Scene Dialogue (BSD) Translation task.

Data Augmentation Machine Translation +1