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

Existing multilingual machine translation approaches mainly focus on English-centric directions, while the non-English directions still lag behind. In this work, we aim to build a many-to-many translation system with an emphasis on the quality of non-English language directions. Our intuition is based on the hypothesis that a universal cross-language representation leads to better multilingual translation performance. To this end, we propose \method, a training method to obtain a single unified multilingual translation model. mCOLT is empowered by two techniques: (i) a contrastive learning scheme to close the gap among representations of different languages, and (ii) data augmentation on both multiple parallel and monolingual data to further align token representations. For English-centric directions, mCOLT achieves competitive or even better performance than a strong pre-trained model mBART on tens of WMT benchmarks. For non-English directions, mCOLT achieves an improvement of average 10+ BLEU compared with the multilingual baseline.