Neural Machine Translation models are brittle to input noise. Current robustness techniques mostly adapt models to existing noisy texts, but these models generally fail when faced with unseen noise and their performance degrades on clean texts. In this paper, we introduce the idea of visual context to improve translation robustness against noisy texts. In addition, we propose a novel error correction training regime by treating error correction as an auxiliary task to further improve robustness. Experiments on English-French and English-German translation show that both multimodality and error correction training are beneficial for model robustness to known and new types of errors, while keeping the quality on clean texts.

翻译：神经机器翻译模型对输入噪音来说是易碎的。 目前的稳健性技术大多使模型适应于现有的吵闹文本,但这些模型在面对隐蔽噪音时通常会失败,其性能在干净文本上会退化。 在本文中,我们引入视觉背景概念,以提高翻译对吵闹文本的稳健性。此外,我们提出一个新的错误纠正培训制度,将错误纠正作为进一步提高稳健性的辅助任务。 英法和英德翻译实验显示,多式联运和错误纠正培训都有利于模型对已知和新类型的错误的稳健性,同时保持干净文本的质量。