Back-translation for Large-Scale Multilingual Machine Translation

09/17/2021
by   Baohao Liao, et al.
0

This paper illustrates our approach to the shared task on large-scale multilingual machine translation in the sixth conference on machine translation (WMT-21). This work aims to build a single multilingual translation system with a hypothesis that a universal cross-language representation leads to better multilingual translation performance. We extend the exploration of different back-translation methods from bilingual translation to multilingual translation. Better performance is obtained by the constrained sampling method, which is different from the finding of the bilingual translation. Besides, we also explore the effect of vocabularies and the amount of synthetic data. Surprisingly, the smaller size of vocabularies perform better, and the extensive monolingual English data offers a modest improvement. We submitted to both the small tasks and achieved the second place.

READ FULL TEXT
research
04/08/2022

MMTAfrica: Multilingual Machine Translation for African Languages

In this paper, we focus on the task of multilingual machine translation ...
research
05/20/2021

Contrastive Learning for Many-to-many Multilingual Neural Machine Translation

Existing multilingual machine translation approaches mainly focus on Eng...
research
03/11/2021

Towards Continual Learning for Multilingual Machine Translation via Vocabulary Substitution

We propose a straightforward vocabulary adaptation scheme to extend the ...
research
09/28/2020

Deep Transformers with Latent Depth

The Transformer model has achieved state-of-the-art performance in many ...
research
05/07/2023

Leveraging Synthetic Targets for Machine Translation

In this work, we provide a recipe for training machine translation model...
research
11/03/2021

Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task

This report describes Microsoft's machine translation systems for the WM...
research
04/16/2021

Serial or Parallel? Plug-able Adapter for multilingual machine translation

Developing a unified multilingual translation model is a key topic in ma...

Please sign up or login with your details

Forgot password? Click here to reset