Multi-modal machine translation (MMT) improves translation quality by introducing visual information. However, the existing MMT model ignores the problem that the image will bring information irrelevant to the text, causing much noise to the model and affecting the translation quality. In this paper, we propose a novel Gumbel-Attention for multi-modal machine translation, which selects the text-related parts of the image features. Specifically, different from the previous attention-based method, we first use a differentiable method to select the image information and automatically remove the useless parts of the image features. Through the score matrix of Gumbel-Attention and image features, the image-aware text representation is generated. And then, we independently encode the text representation and the image-aware text representation with the multi-modal encoder. Finally, the final output of the encoder is obtained through multi-modal gated fusion. Experiments and case analysis proves that our method retains the image features related to the text, and the remaining parts help the MMT model generates better translations.
Download