mlsanityData to 7 Oct 2026

Centroid-Based Efficient Minimum Bayes Risk Decoding

arXiv 2402.11197 ↗First posted 17 Feb 2024cs.CLcited by 12

Not on the map. Why?

Abstract (arXiv)

Minimum Bayes risk (MBR) decoding achieved state-of-the-art translation performance by using COMET, a neural metric that has a high correlation with human evaluation. However, MBR decoding requires quadratic time since it computes the expected score between a translation hypothesis and all reference translations. We propose centroid-based MBR (CBMBR) decoding to improve the speed of MBR decoding. Our method clusters the reference translations in the feature space, and then calculates the score using the centroids of each cluster. The experimental results show that our CBMBR not only improved the decoding speed of the expected score calculation 5.7 times, but also outperformed vanilla MBR decoding in translation quality by up to 0.5 COMET in the WMT'22 EnleftrightarrowJa, EnleftrightarrowDe, EnleftrightarrowZh, and WMT'23 EnleftrightarrowJa translation tasks.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 15 of its 32 references that are in the map. First posted on arXiv 17 Feb 2024.

Builds on

15 of 32 references.

References · 15

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  4. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  5. 2020COMET: A Neural Framework for MT Evaluationcited by 1,024
  6. 2017SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluationcited by 998
  7. 2016Bag of Tricks for Efficient Text Classificationcited by 869
  8. 2020Language-agnostic BERT Sentence Embeddingcited by 621
  9. 2020Beyond English-Centric Multilingual Machine Translationcited by 559
  10. 2020Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translationcited by 137
  11. 2021Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translationcited by 63
  12. 2023Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translationcited by 57
3 more
  1. 2021Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translationcited by 56
  2. 2023Faster Minimum Bayes Risk Decoding with Confidence-based Pruningcited by 34
  3. 2024Linear-time Minimum Bayes Risk Decoding with Reference Aggregationcited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 5; 2026: 1.

12 papers.

  1. 2024Mitigating Metric Bias in Minimum Bayes Risk Decodingcited by 15
  2. 2024Improving Minimum Bayes Risk Decoding with Multi-Promptcited by 13
  3. 2024mbrs: A Library for Minimum Bayes Risk Decodingcited by 13
  4. 2024Diversity Explains Inference Scaling Laws: Through a Case Study of Minimum Bayes Risk Decodingcited by 8
  5. 2024A Bayesian Optimization Approach to Machine Translation Rerankingcited by 2
  6. 2025Early-Exit and Instant Confidence Translation Quality Estimationcited by 2
  7. 2025Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognitioncited by 2
  8. 2025Agreement-Constrained Probabilistic Minimum Bayes Risk Decodingcited by 2
  9. 2025Case-Based Decision-Theoretic Decoding with Quality Memoriescited by 1
  10. 2024Unveiling the Power of Source: Source-based Minimum Bayes Risk Decoding for Neural Machine Translationcited by 0
  11. 2025Minimum Bayes Risk Decoding for Error Span Detection in Reference-Free Automatic Machine Translation Evaluationcited by 0
  12. 2026Quit While You're Ahead: Quit for Efficient Candidate Generation in Machine Translation Rerankingcited by 0