arxivst stuff from arxiv that you should probably bookmark

Towards String-to-Tree Neural Machine Translation

Abstract · Apr 16, 2017 09:54 ·

nmt syntactic smt tree syntax reordering translation linearized cs-cl

Arxiv Abstract

  • Roee Aharoni
  • Yoav Goldberg

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.

Read the paper (pdf) »