Unveiling the Power of Source: Source-based Minimum Bayes Risk Decoding for Neural Machine Translation
Boxuan Lyu, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura
Abstract
Maximum a posteriori decoding, a commonly used method for neural machine translation (NMT), aims to maximize the estimated posterior probability. However, high estimated probability does not always lead to high translation quality. Minimum Bayes Risk (MBR) decoding offers an alternative by seeking hypotheses with the highest expected utility.Inspired by Quality Estimation (QE) reranking which uses the QE model as a ranker, we propose source-based MBR (sMBR) decoding, a novel approach that utilizes quasi-sources (generated via paraphrasing or back-translation) as “support hypotheses” and a reference-free quality estimation metric as the utility function, marking the first work to solely use sources in MBR decoding. Experiments show that sMBR outperforms QE reranking and the standard MBR decoding. Our findings suggest that sMBR is a promising approach for NMT decoding.
BibTeX
@inproceedings{lyu-etal-2025-unveiling,
title = "Unveiling the Power of Source: Source-based Minimum {B}ayes Risk Decoding for Neural Machine Translation",
author = "Lyu, Boxuan and
Kamigaito, Hidetaka and
Funakoshi, Kotaro and
Okumura, Manabu",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.149/",
doi = "10.18653/v1/2025.acl-long.149",
pages = "2976--2994",
ISBN = "979-8-89176-251-0"
}