A Visual Attention Grounding Neural Model for Multimodal Machine Translation
share
We introduce a novel multimodal machine translation model that utilizes parallel visual and textual information. Our model jointly optimizes the learning of a shared visual-language embedding and translating languages. It does this with the aid of a visual attention grounding mechanism which links the visual semantics in the image with the corresponding textual semantics. Our approach achieves competitive state-of-the-art results on the Multi30K and the Ambiguous COCO datasets. We also collected a new multilingual multimodal product description dataset to simulate a real-world international online shopping scenario. On this dataset, our visual attention grounding model outperforms other methods by a large margin.
READ FULL TEXT