We explore strategies for incorporating target syntax into Neural Machine Translation. We specifically focus on syntax in ensembles containing multiple sentence representations. We formulate beam search over such ensembles using WFSTs, and describe a delayed SGD update training procedure that is especially effective for long representations like linearized syntax. Our approach gives state-of-the-art performance on a difficult Japanese-English task.
CITATION STYLE
Saunders, D., Stahlberg, F., De Gispert, A., & Byrne, B. (2018). Multi-representation ensembles and delayed SGD updates improve syntax-based NMT. In ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) (Vol. 2, pp. 319–325). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/p18-2051
Mendeley helps you to discover research relevant for your work.