Towards String-to-Tree Neural Machine Translation

2017/04/16 by Aharoni, Roee, Goldberg, Yoav
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1704.04743

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.

Related

• A Tree-based Decoder for Neural Machine Translation
• Top-down Tree Structured Decoding with Syntactic Connections for Neural Machine Translation and Parsing
• Inducing Constituency Trees through Neural Machine Translation
• Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder
• Incorporating Syntactic Uncertainty in Neural Machine Translation with Forest-to-Sequence Model