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.

本篇研究介绍了 Facebook AI 对 WMT20 共享新闻翻译任务的参赛，主要关注于资源有限的环境中，用多种策略和技术如自监督模型预训练、多语言模型、数据增强、标签数据微调等，以对目标新闻领域适应来应对低资源问题。在测试集上，我们的最佳提交系统分别取得 21.5 和 13.7 的 BLEU 得分，适用于 Ta→En 和 En→Ta，以及 27.9 和 13.0 的分数适用于 Iu→En 和 En→Iu。

Facebook AI 的 WMT20 新闻翻译任务提交

Facebook AI's WMT20 News Translation Task Submission

This paper describes our submission to the WMT20 sentence filtering task. We
combine scores from (1) a custom LASER built for each source language, (2) a
classifier built to distinguish positive and negative pairs by semantic
alignment, and (3) the original scores included in the task devkit. For the
mBART finetuning setup, provided by the organizers, our method shows 7% and 5%
relative improvement over baseline, in sacreBLEU score on the test set for
Pashto and Khmer respectively.

本文介绍了我们在 WMT20 句子过滤任务中的提交，通过结合每种源语言的自定义 LASER 的分数、用于区分正负配对的语义对齐的分类器的分数和任务开发套件中包含的原始分数，我们在 mBART 微调设置中取得了不错的成效，在 Pashto 和 Khmer 上相对于基线分别提高了 7% 和 5% 的 sacreBLEU 分数。

改进低资源条件下平行语料库过滤的得分组合方法

Score Combination for Improved Parallel Corpus Filtering for Low  Resource Conditions

This paper describes our VolcTrans system on WMT20 shared news translation
task. We participated in 8 translation directions. Our basic systems are based
on Transformer, with several variants (wider or deeper Transformers, dynamic
convolutions). The final system includes text pre-process, data selection,
synthetic data generation, advanced model ensemble, and multilingual
pre-training.

介绍我们在 WMT20 共享新闻翻译任务中使用的 VolcTrans 系统，该系统基于 Transformer，包括文本预处理、数据选择、合成数据生成、高级模型集成和多语言预训练。