Multi-modal neural machine translation (NMT) aims to translate source
sentences into a target language paired with images. However, dominant
multi-modal NMT models do not fully exploit fine-grained semantic
correspondences between semantic units of different modalities, which have
potential to refine multi-modal representation learning. To deal with this
issue, in this paper, we propose a novel graph-based multi-modal fusion encoder
for NMT. Specifically, we first represent the input sentence and image using a
unified multi-modal graph, which captures various semantic relationships
between multi-modal semantic units (words and visual objects). We then stack
multiple graph-based multi-modal fusion layers that iteratively perform
semantic interactions to learn node representations. Finally, these
representations provide an attention-based context vector for the decoder. We
evaluate our proposed encoder on the Multi30K datasets. Experimental results
and in-depth analysis show the superiority of our multi-modal NMT model.

本论文提出了一种新型的基于图的多模态融合编码器，用于多模态神经机器翻译（NMT）中利用不同模态语义单元之间的细粒度语义对应关系，以优化多模态表示学习，并在 Multi30K 数据集上验证了模型的卓越性能。

一种基于图形的多模态融合编码器在神经机器翻译中的应用

A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine  Translation

In this work, we propose to model the interaction between visual and textual
features for multi-modal neural machine translation (MMT) through a latent
variable model. This latent variable can be seen as a multi-modal stochastic
embedding of an image and its description in a foreign language. It is used in
a target-language decoder and also to predict image features. Importantly, our
model formulation utilises visual and textual inputs during training but does
not require that images be available at test time. We show that our latent
variable MMT formulation improves considerably over strong baselines, including
a multi-task learning approach (Elliott and K\'ad\'ar, 2017) and a conditional
variational auto-encoder approach (Toyama et al., 2016). Finally, we show
improvements due to (i) predicting image features in addition to only
conditioning on them, (ii) imposing a constraint on the minimum amount of
information encoded in the latent variable, and (iii) by training on additional
target-language image descriptions (i.e. synthetic data).

本研究提出一种多模态神经机器翻译模型，通过潜在变量模型来建模视觉和文本特征之间的交互，预测图像特征和提高翻译性能，可以在训练阶段利用视觉和文本输入，而在测试阶段不需要图像输入，通过预测图像特征等优化，同时利用合成数据等附加训练方式进一步提高翻译性能。

多模翻译的隐变量模型

Latent Variable Model for Multi-modal Translation

We introduce a Multi-modal Neural Machine Translation model in which a
doubly-attentive decoder naturally incorporates spatial visual features
obtained using pre-trained convolutional neural networks, bridging the gap
between image description and translation. Our decoder learns to attend to
source-language words and parts of an image independently by means of two
separate attention mechanisms as it generates words in the target language. We
find that our model can efficiently exploit not just back-translated in-domain
multi-modal data but also large general-domain text-only MT corpora. We also
report state-of-the-art results on the Multi30k data set.

我们引入了一种多模态神经机器翻译模型，其中双重注意力解码器自然地整合了使用预先训练的卷积神经网络获取的空间视觉特征，弥合了图像描述和翻译之间的差距。我们的解码器通过两个独立的注意机制在生成目标语言单词时独立地关注源语言单词和图像的部分。我们发现我们的模型不仅可以高效地利用反向翻译的域内 多模态数据，还可以利用大规模的通用领域文本翻译语料库。我们还在 Multi30k 数据集上报告了最先进的结果。