Towards String-To-Tree Neural Machine Translation
Roee Aharoni, Yoav Goldberg · 2017
We present a simple method to incorporate syntactic information about the target language in a neural machine translation system by translating into linearized, lexicalized constituency trees.Experiments on the WMT16 German-English news translation task shown improved BLEU scores when compared to a syntax-agnostic NMT baseline trained on the same dataset.An analysis of the translations from the syntax-aware system shows that it performs more reordering during translation in comparison to the baseline.A smallscale human evaluation also showed an advantage to the syntax-aware system.