Towards String-To-Tree Neural Machine Translation

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.
Anthology ID:
P17-2021
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
132–140
Language:
URL:
https://aclanthology.org/P17-2021
DOI:
10.18653/v1/P17-2021
Bibkey:
Cite (ACL):
Roee Aharoni and Yoav Goldberg. 2017. Towards String-To-Tree Neural Machine Translation. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 132–140, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Towards String-To-Tree Neural Machine Translation (Aharoni & Goldberg, ACL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/P17-2021.pdf
Presentation:
 P17-2021.Presentation.pdf
Video:
 https://vimeo.com/234955359
Data
WMT 2016