论文标题
构建服务任意X-y翻译的多语言机器翻译系统
Building Multilingual Machine Translation Systems That Serve Arbitrary X-Y Translations
论文作者
论文摘要
多语言神经机器翻译（MNMT）使一个系统可以将句子从多种源语言转换为多种目标语言，与传统的双语系统相比，大大降低了部署成本。但是，MNMT培训益处通常仅限于多一对一的方向。该模型在一对一的表现不佳，并且在零弹位设置中遭受了多种影响。为了解决这个问题，本文讨论了如何实际构建提供任意X-y翻译指示的MNMT系统，同时使用两阶段的训练策略进行预训练和填充策略来利用多语言。尝试WMT'21多语言翻译任务，我们证明了我们的系统的表现优于大多数方向的直接双语模型和枢轴翻译模型的传统基线，而无需进行架构变化或额外的数据收集而无需提供+6.0和+4.1 BLEU。此外，我们还在极大的数据设置中检查了我们提出的方法，以适应实际的部署方案。
Multilingual Neural Machine Translation (MNMT) enables one system to translate sentences from multiple source languages to multiple target languages, greatly reducing deployment costs compared with conventional bilingual systems. The MNMT training benefit, however, is often limited to many-to-one directions. The model suffers from poor performance in one-to-many and many-to-many with zero-shot setup. To address this issue, this paper discusses how to practically build MNMT systems that serve arbitrary X-Y translation directions while leveraging multilinguality with a two-stage training strategy of pretraining and finetuning. Experimenting with the WMT'21 multilingual translation task, we demonstrate that our systems outperform the conventional baselines of direct bilingual models and pivot translation models for most directions, averagely giving +6.0 and +4.1 BLEU, without the need for architecture change or extra data collection. Moreover, we also examine our proposed approach in an extremely large-scale data setting to accommodate practical deployment scenarios.
