Despite the fact that multilingual agreement (MA) has shown its importance for multilingual neural machine translation (MNMT), current methodologies in the field have two shortages: (i) require parallel data between multiple language pairs, which is not always realistic and (ii) optimize the agreement in an ambiguous direction, which hampers the translation performance. We present \textbf{B}idirectional \textbf{M}ultilingual \textbf{A}greement via \textbf{S}witched \textbf{B}ack-\textbf{t}ranslation (\textbf{BMA-SBT}), a novel and universal multilingual agreement framework for fine-tuning pre-trained MNMT models, which (i) exempts the need for aforementioned parallel data by using a novel method called switched BT that creates synthetic text written in another source language using the translation target and (ii) optimizes the agreement bidirectionally with the Kullback-Leibler Divergence loss. Experiments indicate that BMA-SBT clearly improves the strong baselines on the task of MNMT with three benchmarks: TED Talks, News, and Europarl. In-depth analyzes indicate that BMA-SBT brings additive improvements to the conventional BT method.

翻译：尽管多语言一致性（Multilingual Agreement, MA）已被证明对多语言神经机器翻译（Multilingual Neural Machine Translation, MNMT）具有重要性，但当前领域中的方法存在两个不足：（i）需要多个语言对之间的平行数据，这在现实中往往难以实现；（ii）以模糊的方向优化一致性，从而削弱翻译性能。我们提出了一种新颖且通用的多语言一致性框架——基于切换回译的双向多语言一致性（Bidirectional Multilingual Agreement via Switched Back-translation, BMA-SBT），用于微调预训练的MNMT模型。该框架通过以下方式克服上述不足：（i）采用名为“切换回译”的新方法，利用翻译目标生成另一种源语言的合成文本，从而避免了对上述平行数据的需求；（ii）使用Kullback-Leibler散度损失函数双向优化一致性。实验表明，在TED Talks、News和Europarl三个基准测试中，BMA-SBT显著提升了MNMT任务的强基线性能。深入分析进一步表明，BMA-SBT为传统回译方法带来了叠加性改进。