EdinSaar@WMT21: North-Germanic Low-Resource Multilingual NMT
This work addresses translation challenges for low-resource languages like Icelandic, Norwegian, and Swedish, but it is incremental as it applies existing methods to a specific domain.
The paper tackled multilingual low-resource translation for North Germanic languages, achieving top performance in most directions at the WMT2021 shared task.
We describe the EdinSaar submission to the shared task of Multilingual Low-Resource Translation for North Germanic Languages at the Sixth Conference on Machine Translation (WMT2021). We submit multilingual translation models for translations to/from Icelandic (is), Norwegian-Bokmal (nb), and Swedish (sv). We employ various experimental approaches, including multilingual pre-training, back-translation, fine-tuning, and ensembling. In most translation directions, our models outperform other submitted systems.