Facebook AI’s WMT20 News Translation Task Submission
By Peng-Jen Chen, Ann Lee, Changhan Wang, Naman Goyal, Angela Fan, Mary Williamson, Jiatao Gu. 2020
38 citations recorded by the source corpus.
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.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Ondrej Bojar
- Markus Freitag
- Philipp Koehn
- Felix Stahlberg
- Tom Kocmi
- Graham Neubig
- Barry Haddow
- Yvette Graham
Citations in the corpus
- Findings of the 2020 Conference on Machine Translation (WMT20) (2020, methodology): “2.3.10 FACEBOOK AI (Chen et al., 2020a) FACEBOOK AI focus on low-resource language pairs involving Inuktitut and Tamil using two strategies: (1) exploiting all available data (parallel and monolingual from all languages) and (2) adapting the model to the test domain.”
- DUB: Discrete Unit Back-translation for Speech Translation (2023, background): “…challenges faced by ST is data scarcity, which is similar to the low-resource scenarios encountered in MT. Intuitively, techniques developed for low-resource MT (Imamura et al., 2018; Xia et al., 2019; Chen et al., 2020; Liu et al., 2020 et al., 2020) should be utilized to improve ST performance.”