# Syntactically Guided Neural Machine Translation

arXiv: https://arxiv.org/abs/1605.04569 · HTML: https://mlsanity.com/paper/1605.04569/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 May 2016.

## Built on by (most cited first, 3 of 3)

- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [First the worst: Finding better gender translations during beam search](https://mlsanity.com/paper/2104.07429/) (2021)
- [GrammaMT: Improving Machine Translation with Grammar-Informed In-Context Learning](https://mlsanity.com/paper/2410.18702/) (2024)

## Abstract (arXiv)

We investigate the use of hierarchical phrase-based SMT lattices in end-to-end neural machine translation (NMT). Weight pushing transforms the Hiero scores for complete translation hypotheses, with the full translation grammar score and full n-gram language model score, into posteriors compatible with NMT predictive probabilities. With a slightly modified NMT beam-search decoder we find gains over both Hiero and NMT decoding alone, with practical advantages in extending NMT to very large input and output vocabularies.