DeepAI AI Chat
Log In Sign Up

Language-Aware Multilingual Machine Translation with Self-Supervised Learning

by   Haoran Xu, et al.
Johns Hopkins University

Multilingual machine translation (MMT) benefits from cross-lingual transfer but is a challenging multitask optimization problem. This is partly because there is no clear framework to systematically learn language-specific parameters. Self-supervised learning (SSL) approaches that leverage large quantities of monolingual data (where parallel data is unavailable) have shown promise by improving translation performance as complementary tasks to the MMT task. However, jointly optimizing SSL and MMT tasks is even more challenging. In this work, we first investigate how to utilize intra-distillation to learn more *language-specific* parameters and then show the importance of these language-specific parameters. Next, we propose a novel but simple SSL task, concurrent denoising, that co-trains with the MMT task by concurrently denoising monolingual data on both the encoder and decoder. Finally, we apply intra-distillation to this co-training approach. Combining these two approaches significantly improves MMT performance, outperforming three state-of-the-art SSL methods by a large margin, e.g., 11.3% and 3.7% improvement on an 8-language and a 15-language benchmark compared with MASS, respectively


page 5

page 9


Multi-task Learning for Multilingual Neural Machine Translation

While monolingual data has been shown to be useful in improving bilingua...

Cross-lingual Retrieval for Iterative Self-Supervised Training

Recent studies have demonstrated the cross-lingual alignment ability of ...

The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains

Recent model pruning methods have demonstrated the ability to remove red...

Integrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languages

For most language combinations, parallel data is either scarce or simply...

Improved Cross-Lingual Transfer Learning For Automatic Speech Translation

Research in multilingual speech-to-text translation is topical. Having a...

OmniKnight: Multilingual Neural Machine Translation with Language-Specific Self-Distillation

Although all-in-one-model multilingual neural machine translation (MNMT)...

PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence Pretraining

Despite the success of multilingual sequence-to-sequence pretraining, mo...