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.
@article{arxiv.1704.06393,
title = {Neural System Combination for Machine Translation},
author = {Long Zhou and Wenpeng Hu and Jiajun Zhang and Chengqing Zong},
journal= {arXiv preprint arXiv:1704.06393},
year = {2017}
}