# Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions

arXiv: https://arxiv.org/abs/1610.01108 · HTML: https://mlsanity.com/paper/1610.01108/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2016.

## Built on by (most cited first, 7 of 7)

- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [AraT5: Text-to-Text Transformers for Arabic Language Generation](https://mlsanity.com/paper/2109.12068/) (2021)
- [First the worst: Finding better gender translations during beam search](https://mlsanity.com/paper/2104.07429/) (2021)
- [Revisiting Checkpoint Averaging for Neural Machine Translation](https://mlsanity.com/paper/2210.11803/) (2022)
- [Translating the Unseen? Yoruba-English MT in Low-Resource, Morphologically-Unmarked Settings](https://mlsanity.com/paper/2103.04225/) (2021)
- [Instability in Downstream Task Performance During LLM Pretraining](https://mlsanity.com/paper/2510.04848/) (2025)
- [Assessing the Impact of Typological Features on Multilingual Machine Translation in the Age of Large Language Models](https://mlsanity.com/paper/2602.03551/) (2026)

## Abstract (arXiv)

In this paper we provide the largest published comparison of translation quality for phrase-based SMT and neural machine translation across 30 translation directions. For ten directions we also include hierarchical phrase-based MT. Experiments are performed for the recently published United Nations Parallel Corpus v1.0 and its large six-way sentence-aligned subcorpus. In the second part of the paper we investigate aspects of translation speed, introducing AmuNMT, our efficient neural machine translation decoder. We demonstrate that current neural machine translation could already be used for in-production systems when comparing words-per-second ratios.