We present M3P, a Multitask Multilingual Multimodal Pre-trained model that combines multilingual pre-training and multimodal pre-training into a unified framework via multitask pre-training. Our goal is to learn universal representations that can map objects occurred in different modalities or texts expressed in different languages into a common semantic space. In addition, to explicitly encourage fine-grained alignment between images and non-English languages, we also propose Multimodal Code-switched Training (MCT) to combine monolingual pre-training and multimodal pre-training via a code-switch strategy. Experiments are performed on the multilingual image retrieval task across two benchmark datasets, including MSCOCO and Multi30K. M3P can achieve comparable results for English and new state-of-the-art results for non-English languages.
@article{arxiv.2006.02635,
title = {M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training},
author = {Minheng Ni and Haoyang Huang and Lin Su and Edward Cui and Taroon Bharti and Lijuan Wang and Jianfeng Gao and Dongdong Zhang and Nan Duan},
journal= {arXiv preprint arXiv:2006.02635},
year = {2021}
}