Multilingual Non-Autoregressive Machine Translation without Knowledge Distillation
Chenyang Huang, Fei Huang, Zaixiang Zheng, Osmar R. Zai͏̈ane, Hao Zhou, Lili Mou · 2023
Multilingual neural machine translation (MNMT) aims at using one single model for multiple translation directions.Recent work applies non-autoregressive Transformers to improve the efficiency of MNMT, but requires expensive knowledge distillation (KD) processes.To this end, we propose an M-DAT approach to non-autoregressive multilingual machine translation.Our system leverages the recent advance of the directed acyclic Transformer (DAT), which does not require KD.We further propose a pivot back-translation (PivotBT) approach to improve the generalization to unseen translation directions.Experiments show that our M-DAT achieves state-of-the-art performance in non-autoregressive MNMT. 1