mlsanityData to 14 Oct 2026

Chasing COMET: Leveraging Minimum Bayes Risk Decoding for Self-Improving Machine Translation

arXiv 2405.11937 ↗First posted 20 May 2024cs.CL cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

This paper explores Minimum Bayes Risk (MBR) decoding for self-improvement in machine translation (MT), particularly for domain adaptation and low-resource languages. We implement the self-improvement process by fine-tuning the model on its MBR-decoded forward translations. By employing COMET as the MBR utility metric, we aim to achieve the reranking of translations that better aligns with human preferences. The paper explores the iterative application of this approach and the potential need for language-specific MBR utility metrics. The results demonstrate significant enhancements in translation quality for all examined language pairs, including successful application to domain-adapted models and generalisation to low-resource settings. This highlights the potential of COMET-guided MBR for efficient MT self-improvement in various scenarios.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 20 of its 41 references that are in the map. First posted on arXiv 20 May 2024.

Builds on

20 of 41 references.

References · 20

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  3. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  4. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  5. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
  6. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,203
  7. 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
  8. 2023Reinforced Self-Training (ReST) for Language Modelingcited by 500
  9. 2022CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Taskcited by 207
  10. 2018Marian: Fast Neural Machine Translation in C++cited by 203
  11. 2022Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuningcited by 149
  12. 2021High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metricscited by 104
8 more
  1. 2023Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translationcited by 58
  2. 2023An Open Dataset and Model for Language Identificationcited by 50
  3. 2022Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMETcited by 41
  4. 2023MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methodscited by 33
  5. 2021Many-to-English Machine Translation Tools, Data, and Pretrained Modelscited by 31
  6. 2023The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metricscited by 15
  7. 2024Don't Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimationcited by 13
  8. 2022Adam Mickiewicz University at WMT 2022: NER-Assisted and Quality-Aware Neural Machine Translationcited by 5

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 4.

6 papers.

  1. 2024Mitigating Metric Bias in Minimum Bayes Risk Decodingcited by 16
  2. 2024Pitfalls and Outlooks in Using COMETcited by 10
  3. 2025Solving the Unsolvable: Translating Case Law in Hong Kongcited by 3
  4. 2025Optimal Policy Minimum Bayesian Riskcited by 2
  5. 2025TransLaw: A Large-Scale Dataset and Multi-Agent Benchmark Simulating Professional Translation of Hong Kong Case Lawcited by 2
  6. 2025Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transportcited by 0