Miðeind's WMT 2021 submission
Incremental improvement for machine translation in low-resource language pairs.
The paper tackled machine translation for English-Icelandic language pairs by iteratively generating backtranslations and adapting a pretrained mBART-25 model, achieving unspecified results without concrete numbers.
We present Miðeind's submission for the English$\to$Icelandic and Icelandic$\to$English subsets of the 2021 WMT news translation task. Transformer-base models are trained for translation on parallel data to generate backtranslations iteratively. A pretrained mBART-25 model is then adapted for translation using parallel data as well as the last backtranslation iteration. This adapted pretrained model is then used to re-generate backtranslations, and the training of the adapted model is continued.