# Iterative Refinement for Machine Translation

arXiv: https://arxiv.org/abs/1610.06602 · HTML: https://mlsanity.com/paper/1610.06602/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Oct 2016.

## Built on by (most cited first, 5 of 5)

- [Iterative Translation Refinement with Large Language Models](https://mlsanity.com/paper/2306.03856/) (2023)
- [Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design](https://mlsanity.com/paper/2502.14944/) (2025)
- [Extrapolative Controlled Sequence Generation via Iterative Refinement](https://mlsanity.com/paper/2303.04562/) (2023)
- [Hierarchical Context Tagging for Utterance Rewriting](https://mlsanity.com/paper/2206.11218/) (2022)
- [A proof of contribution in blockchain using game theoretical deep learning model](https://mlsanity.com/paper/2409.07460/) (2024)

## Abstract (arXiv)

Existing machine translation decoding algorithms generate translations in a strictly monotonic fashion and never revisit previous decisions. As a result, earlier mistakes cannot be corrected at a later stage. In this paper, we present a translation scheme that starts from an initial guess and then makes iterative improvements that may revisit previous decisions. We parameterize our model as a convolutional neural network that predicts discrete substitutions to an existing translation based on an attention mechanism over both the source sentence as well as the current translation output. By making less than one modification per sentence, we improve the output of a phrase-based translation system by up to 0.4 BLEU on WMT15 German-English translation.