Facebook AI's WMT20 News Translation Task Submission
Peng-Jen Chen, Ann Lee, Changhan Wang, Naman Goyal, Angela Fan, Mary, Williamson, Jiatao Gu

TL;DR
This paper details Facebook AI's low-resource neural machine translation system for WMT20, utilizing data augmentation, domain adaptation, and multilingual techniques to improve translation quality for Tamil and Inuktitut language pairs.
Contribution
The paper introduces an integrated training pipeline combining multiple techniques for low-resource translation, achieving state-of-the-art results on Tamil and Inuktitut language pairs.
Findings
Best systems achieved BLEU scores of 21.5 (Ta->En) and 13.7 (En->Ta)
Data augmentation and domain adaptation improved translation quality
Multilingual and self-supervised pretraining contributed to performance gains
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNatural Language Processing Techniques · Topic Modeling · Multimodal Machine Learning Applications
