# STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework

arXiv: https://arxiv.org/abs/1810.08398 · HTML: https://mlsanity.com/paper/1810.08398/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2018.

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

- [Learning When to Translate for Streaming Speech](https://mlsanity.com/paper/2109.07368/) (2021)
- [BSTC: A Large-Scale Chinese-English Speech Translation Dataset](https://mlsanity.com/paper/2104.03575/) (2021)
- [StreamingThinker: Large Language Models Can Think While Reading](https://mlsanity.com/paper/2510.17238/) (2025)
- [LEAPT: Learning Adaptive Prefix-to-prefix Translation For Simultaneous Machine Translation](https://mlsanity.com/paper/2303.11750/) (2023)

## Abstract (arXiv)

Simultaneous translation, which translates sentences before they are finished, is useful in many scenarios but is notoriously difficult due to word-order differences. While the conventional seq-to-seq framework is only suitable for full-sentence translation, we propose a novel prefix-to-prefix framework for simultaneous translation that implicitly learns to anticipate in a single translation model. Within this framework, we present a very simple yet surprisingly effective wait-k policy trained to generate the target sentence concurrently with the source sentence, but always k words behind. Experiments show our strategy achieves low latency and reasonable quality (compared to full-sentence translation) on 4 directions: zh<->en and de<->en.