# Midheind's WMT 2021 submission

arXiv: https://arxiv.org/abs/2109.07343 · HTML: https://mlsanity.com/paper/2109.07343/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 18 references that are in the map.
- First posted on arXiv 15 Sep 2021.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEB](https://mlsanity.com/paper/1911.04944/) (2019)
- [Detecting Hallucinated Content in Conditional Neural Sequence Generation](https://mlsanity.com/paper/2011.02593/) (2020)
- [Tensor2Tensor for Neural Machine Translation](https://mlsanity.com/paper/1803.07416/) (2018)
- [Language Technology Programme for Icelandic 2019-2023](https://mlsanity.com/paper/2003.09244/) (2020)

## Built on by (most cited first, 3 of 3)

- [Multilingual Bidirectional Unsupervised Translation Through Multilingual Finetuning and Back-Translation](https://mlsanity.com/paper/2209.02821/) (2022)
- [Cross-Lingual QA as a Stepping Stone for Monolingual Open QA in Icelandic](https://mlsanity.com/paper/2207.01918/) (2022)
- [Contrastive Decoding for Synthetic Data Generation in Low-Resource Language Modeling](https://mlsanity.com/paper/2510.08245/) (2025)

## Abstract (arXiv)

We present Midheind's submission for the English→Icelandic and Icelandic→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.