论文标题
通过切换的背面翻译对多语言神经机器翻译进行双向修改多语言协议
Revamping Multilingual Agreement Bidirectionally via Switched Back-translation for Multilingual Neural Machine Translation
论文作者
论文摘要
尽管多语言协议（MA）表明了其对多语言神经机器翻译（MNMT）的重要性，但现场的当前方法学有两种短缺：（i）在多种语言对之间需要并行数据，这并不总是现实的，这并不总是现实的，并且（ii）在模棱两可的方向上优化了一致性，这阻碍了翻译性能。我们介绍\ textbf {b} idirectional \ textbf {m}通过\ textbf {s} witched \ textbf {s} witched \ textbf {b} ack- \ textbf {t textbf {t}预先训练的MNMT模型，该模型（i）使用一种称为Switched BT的新方法来免除对上述并行数据的需求，该方法使用Translation Targets创建了用另一种源语言编写的合成文本，并且（ii）（ii）与Kullback-Leibler-Leibler差异损失相比优化协议。实验表明，BMA-SBT显然通过三个基准：TED Talks，News和Europarl来改善MNMT任务的强大基线。深入分析表明，BMA-SBT为常规BT方法带来了添加剂的改进。
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.
