# Vocabulary Selection Strategies for Neural Machine Translation

arXiv: https://arxiv.org/abs/1610.00072 · HTML: https://mlsanity.com/paper/1610.00072/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2016.

## Built on by (most cited first, 4 of 4)

- [Tokenization and the Noiseless Channel](https://mlsanity.com/paper/2306.16842/) (2023)
- [The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation](https://mlsanity.com/paper/2205.06618/) (2022)
- [Online Domain-aware LLM Decoding for Continual Domain Evolution](https://mlsanity.com/paper/2602.08088/) (2026)
- [Efficient Multilingual Neural Machine Translation via Corpus-Driven Vocabulary Pruning: An English-Arabic Case Study](https://mlsanity.com/paper/2608.03480/) (2026)

## Abstract (arXiv)

Classical translation models constrain the space of possible outputs by selecting a subset of translation rules based on the input sentence. Recent work on improving the efficiency of neural translation models adopted a similar strategy by restricting the output vocabulary to a subset of likely candidates given the source. In this paper we experiment with context and embedding-based selection methods and extend previous work by examining speed and accuracy trade-offs in more detail. We show that decoding time on CPUs can be reduced by up to 90% and training time by 25% on the WMT15 English-German and WMT16 English-Romanian tasks at the same or only negligible change in accuracy. This brings the time to decode with a state of the art neural translation system to just over 140 msec per sentence on a single CPU core for English-German.