Saved in:
Bibliographic Details
Main Authors: Huang, Chenyang, Huang, Fei, Zheng, Zaixiang, Zaïane, Osmar R., Zhou, Hao, Mou, Lili
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.04537
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.