# Multi-representation Ensembles and Delayed SGD Updates Improve Syntax-based NMT

arXiv: https://arxiv.org/abs/1805.00456 · HTML: https://mlsanity.com/paper/1805.00456/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2018.

## Built on by (most cited first, 2 of 2)

- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [Top-down string-to-dependency Neural Machine Translation](https://mlsanity.com/paper/2603.27938/) (2026)

## Abstract (arXiv)

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.