Cross-lingual Visual Pre-training for Multimodal Machine Translation
This work addresses the need for improved multimodal translation systems, though it appears incremental as it builds on existing pre-training approaches.
The paper tackles the problem of learning visually-grounded cross-lingual representations by combining cross-lingual and visual pre-training methods, achieving state-of-the-art performance in multimodal machine translation.
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.