# Facebook AI's WMT20 News Translation Task Submission

arXiv: https://arxiv.org/abs/2011.08298 · HTML: https://mlsanity.com/paper/2011.08298/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2020.

## Built on by (most cited first, 17 of 17)

- [TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation](https://mlsanity.com/paper/2109.13296/) (2021)
- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective](https://mlsanity.com/paper/2210.10488/) (2022)
- [GPT-who: An Information Density-based Machine-Generated Text Detector](https://mlsanity.com/paper/2310.06202/) (2023)
- [Machine-Made Media: Monitoring the Mobilization of Machine-Generated Articles on Misinformation and Mainstream News Websites](https://mlsanity.com/paper/2305.09820/) (2023)
- [Quantifying the Dialect Gap and its Correlates Across Languages](https://mlsanity.com/paper/2310.15135/) (2023)
- [DUB: Discrete Unit Back-translation for Speech Translation](https://mlsanity.com/paper/2305.11411/) (2023)
- [EAGLE: A Domain Generalization Framework for AI-generated Text Detection](https://mlsanity.com/paper/2403.15690/) (2024)
- [Is Contrasting All You Need? Contrastive Learning for the Detection and Attribution of AI-generated Text](https://mlsanity.com/paper/2407.09364/) (2024)
- [As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation](https://mlsanity.com/paper/2107.08357/) (2021)
- [The NiuTrans Machine Translation Systems for WMT21](https://mlsanity.com/paper/2109.10485/) (2021)
- [Amortized Noisy Channel Neural Machine Translation](https://mlsanity.com/paper/2112.08670/) (2021)
- [HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints](https://mlsanity.com/paper/2109.04443/) (2021)
- [Extending the Subwording Model of Multilingual Pretrained Models for New Languages](https://mlsanity.com/paper/2211.15965/) (2022)
- [GigaCheck: Detecting LLM-generated Content via Object-Centric Span Localization](https://mlsanity.com/paper/2410.23728/) (2024)
- [POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation](https://mlsanity.com/paper/2401.05596/) (2024)
- [Beyond Vanilla Fine-Tuning: Leveraging Multistage, Multilingual, and Domain-Specific Methods for Low-Resource Machine Translation](https://mlsanity.com/paper/2503.22582/) (2025)

## Abstract (arXiv)

This paper describes Facebook AI's submission to WMT20 shared news translation task. We focus on the low resource setting and participate in two language pairs, Tamil <-> English and Inuktitut <-> English, where there are limited out-of-domain bitext and monolingual data. We approach the low resource problem using two main strategies, leveraging all available data and adapting the system to the target news domain. We explore techniques that leverage bitext and monolingual data from all languages, such as self-supervised model pretraining, multilingual models, data augmentation, and reranking. To better adapt the translation system to the test domain, we explore dataset tagging and fine-tuning on in-domain data. We observe that different techniques provide varied improvements based on the available data of the language pair. Based on the finding, we integrate these techniques into one training pipeline. For En->Ta, we explore an unconstrained setup with additional Tamil bitext and monolingual data and show that further improvement can be obtained. On the test set, our best submitted systems achieve 21.5 and 13.7 BLEU for Ta->En and En->Ta respectively, and 27.9 and 13.0 for Iu->En and En->Iu respectively.