papers AI Learner
The Github is limit! Click to go to the new site.

Towards String-to-Tree Neural Machine Translation

2017-05-06
Roee Aharoni, Yoav Goldberg

Abstract

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. An experiment on the WMT16 German-English news translation task resulted in an improved BLEU score 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 small-scale human evaluation also showed an advantage to the syntax-aware system.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1704.04743

PDF

https://arxiv.org/pdf/1704.04743


下一篇 Geometric GAN

Comments

Content