Pre-trained language models have been shown to improve performance in many natural language tasks substantially. Although the early focus of such models was single language pre-training, recent advances have resulted in cross-lingual and visual pre-training methods. In this paper, we combine these two approaches to learn visually-grounded cross-lingual representations. Specifically, we extend the translation language modelling (Lample and Conneau, 2019) with masked region classification and perform pre-training with three-way parallel vision & language corpora. We show that when fine-tuned for multimodal machine translation, these models obtain state-of-the-art performance. We also provide qualitative insights into the usefulness of the learned grounded representations.
@article{arxiv.2101.10044,
title = {Cross-lingual Visual Pre-training for Multimodal Machine Translation},
author = {Ozan Caglayan and Menekse Kuyu and Mustafa Sercan Amac and Pranava Madhyastha and Erkut Erdem and Aykut Erdem and Lucia Specia},
journal= {arXiv preprint arXiv:2101.10044},
year = {2021}
}