A Visual Attention Grounding Neural Model for Multimodal Machine Translation
This addresses the problem of improving translation accuracy in multimodal contexts for applications like international online shopping, though it appears incremental as it builds on existing attention mechanisms.
The authors tackled multimodal machine translation by developing a model that jointly optimizes visual-language embeddings and translation using visual attention grounding, achieving competitive state-of-the-art results on Multi30K and Ambiguous COCO datasets and outperforming other methods by a large margin on a new multilingual product description dataset.
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 a translator. The model leverages a visual attention grounding mechanism that links the visual semantics 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.