Large language models such as BERT and the GPT series started a paradigm shift that calls for building general-purpose models via pre-training on large datasets, followed by fine-tuning on task-specific datasets. There is now a plethora of large pre-trained models for Natural Language Processing and Computer Vision. Recently, we have seen rapid developments in the joint Vision-Language space as well, where pre-trained models such as CLIP (Radford et al., 2021) have demonstrated improvements in downstream tasks like image captioning and visual question answering. However, surprisingly there is comparatively little work on exploring these models for the task of multimodal machine translation, where the goal is to leverage image/video modality in text-to-text translation. To fill this gap, this paper surveys the landscape of language-and-vision pre-training from the lens of multimodal machine translation. We summarize the common architectures, pre-training objectives, and datasets from literature and conjecture what further is needed to make progress on multimodal machine translation.

翻译：诸如BERT和GPT系列等大型语言模型开启了一种范式转变，即通过在大规模数据集上进行预训练构建通用模型，再针对特定任务数据集进行微调。目前自然语言处理和计算机视觉领域已涌现出大量预训练大模型。近期，视觉-语言联合空间也取得快速发展，其中CLIP (Radford等人, 2021)等预训练模型在图像描述、视觉问答等下游任务中展现了性能提升。然而令人惊讶的是，将这些模型应用于多模态机器翻译任务的研究相对较少——该任务旨在利用图像/视频模态辅助文本到文本的翻译。为填补这一空白，本文从多模态机器翻译视角系统梳理了语言与视觉融合预训练的研究现状。我们总结了文献中常见的架构、预训练目标与数据集，并探讨了推动多模态机器翻译进一步发展所需的关键方向。