We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations. For each sentence, we first retrieve a diversity of images from a shared cross-modal embedding space, which is pre-trained on a large-scale of text-image pairs. Then, the texts and images are respectively encoded by transformer encoder and convolutional neural network. The two sequences of representations are further fused by a simple and effective attention layer. The architecture can be easily applied to text-only natural language processing tasks without manually annotating multimodal parallel corpora. We apply the proposed method on three tasks, including neural machine translation, natural language inference and sequence labeling and experimental results verify the effectiveness.
View on arXiv