M<sup>3</sup>P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training

2021 
We present M 3 P, 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. M 3 P can achieve comparable results for English and new state-of-the-art results for non-English languages.
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    13
    References
    0
    Citations
    NaN
    KQI
    []