通过切换反向翻译实现多语言一致性的双向改进：面向多语言神经机器翻译
Revamping Multilingual Agreement Bidirectionally via Switched Back-translation for Multilingual Neural Machine Translation
AI总结：
针对多语言神经机器翻译中多语言一致性方法依赖平行数据且优化方向模糊的问题，提出BMA-SBT框架，通过切换反向翻译生成合成文本并双向优化一致性，在三个基准上显著提升性能。
摘要：
尽管多语言一致性（MA）已显示出其对多语言神经机器翻译（MNMT）的重要性，当前该领域的方法存在两个不足：（i）需要多种语言对之间的平行数据，这并不总是现实的；（ii）以模糊的方向优化一致性，这阻碍了翻译性能。我们提出了通过切换反向翻译实现的双向多语言一致性（BMA-SBT），这是一种新颖且通用的多语言一致性框架，用于微调预训练的MNMT模型，它（i）通过使用一种称为切换反向翻译的新方法免除了对上述平行数据的需求，该方法利用翻译目标生成用另一种源语言书写的合成文本，并且（ii）使用Kullback-Leibler散度损失双向优化一致性。实验表明，BMA-SBT在三个基准（TED Talks、News和Europarl）上的MNMT任务中明显改善了强基线。深入分析表明，BMA-SBT为传统的反向翻译方法带来了附加改进。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
