Neural machine translation (NMT) becomes a new approach to machine
translation and generates much more fluent results compared to statistical
machine translation (SMT).
However, SMT is usually better than NMT in translation adequacy. It is
therefore a promising direction to combine the advantages of both NMT and SMT.
In this paper, we propose a neural system combination framework leveraging
multi-source NMT, which takes as input the outputs of NMT and SMT systems and
produces the final translation.
Extensive experiments on the Chinese-to-English translation task show that
our model archives significant improvement by 5.3 BLEU points over the best
single system output and 3.4 BLEU points over the state-of-the-art traditional
system combination methods.

本文介绍了一种利用多源神经机器翻译和统计机器翻译输出的神经网络系统组合框架来提高翻译效果的方法，在中英翻译任务中实现了比传统系统组合方法更高的 BLEU 值。

神经系统组合机器翻译

Neural System Combination for Machine Translation

With the advance of technology, entities can be observed in multiple views.
Multiple views containing different types of features can be used for
clustering. Although multi-view clustering has been successfully applied in
many applications, the previous methods usually assume the complete instance
mapping between different views. In many real-world applications, information
can be gathered from multiple sources, while each source can contain multiple
views, which are more cohesive for learning. The views under the same source
are usually fully mapped, but they can be very heterogeneous. Moreover, the
mappings between different sources are usually incomplete and partially
observed, which makes it more difficult to integrate all the views across
different sources. In this paper, we propose MMC (Multi-source Multi-view
Clustering), which is a framework based on collective spectral clustering with
a discrepancy penalty across sources, to tackle these challenges. MMC has
several advantages compared with other existing methods. First, MMC can deal
with incomplete mapping between sources. Second, it considers the disagreements
between sources while treating views in the same source as a cohesive set.
Third, MMC also tries to infer the instance similarities across sources to
enhance the clustering performance. Extensive experiments conducted on
real-world data demonstrate the effectiveness of the proposed approach.

本文提出了一种基于跨源差异惩罚的集体谱聚类框架 —— MMC (多源多视角聚类) 来解决多源数据的多视角聚类问题，该方法考虑了视角间不完全的映射、相容性以及跨源实例相似性等方面，实验表明相比其他方法，MMC 的聚类性能更为有效。