Attention in neural machine translation provides the possibility to encode
relevant parts of the source sentence at each translation step. As a result,
attention is considered to be an alignment model as well. However, there is no
work that specifically studies attention and provides analysis of what is being
learned by attention models. Thus, the question still remains that how
attention is similar or different from the traditional alignment. In this
paper, we provide detailed analysis of attention and compare it to traditional
alignment. We answer the question of whether attention is only capable of
modelling translational equivalent or it captures more information. We show
that attention is different from alignment in some cases and is capturing
useful information other than alignments.

本研究提供详细分析和比较注意力和传统对齐，在一些情况下表明注意力不同于对齐且能捕捉除对齐以外的有用信息。

神经机器翻译中的注意力关注什么？

What does Attention in Neural Machine Translation Pay Attention to?

In this paper, we present a model which takes as input a corpus of images
with relevant spoken captions and finds a correspondence between the two
modalities. We employ a pair of convolutional neural networks to model visual
objects and speech signals at the word level, and tie the networks together
with an embedding and alignment model which learns a joint semantic space over
both modalities. We evaluate our model using image search and annotation tasks
on the Flickr8k dataset, which we augmented by collecting a corpus of 40,000
spoken captions using Amazon Mechanical Turk.

本文提出了一种模型，其将图像和相关的口头描述作为输入，并找到两种模态之间的对应关系。使用一对卷积神经网络在单词级别模拟视觉对象和语音信号，并采用嵌入和对准模型将两个网络联系在一起，以学习跨两种模态的联合语义空间，最终在 Flickr8k 数据集上使用图像搜索和注释任务评估了我们的模型。