Sogou Neural Machine Translation Systems for WMT17

Abstract

We describe the Sogou neural machine translation systems for the WMT 2017 ChineseEnglish news translation tasks. Our systems are based on a multilayer encoder-decoder architecture with attention mechanism. The best translation is obtained with ensemble and reranking techniques. We also propose an approach to improve the named entity translation problem. Our Chi-neseEnglish system achieved the highest cased BLEU among all 20 submitted systems, and our EnglishChinese system ranked the third out of 16 submitted systems. 1