Mi{\dh}eind's WMT 2021 submission

TL;DR

This paper describes Mi{ h}eind's approach to English-Icelandic translation in WMT 2021, combining transformer models, backtranslation, and pretrained mBART-25 adaptation for improved translation quality.

Contribution

It introduces a novel iterative backtranslation and pretrained model adaptation method for low-resource language translation.

Findings

Effective translation performance demonstrated on WMT 2021 tasks.

Iterative backtranslation improves translation quality.

Pretrained mBART-25 adaptation enhances model performance.

Abstract

We present Mi{\dh}eind'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.