mlsanityData to 14 Oct 2026

Unveiling the Power of Source: Source-based Minimum Bayes Risk Decoding for Neural Machine Translation

arXiv 2406.11632 ↗First posted 17 Jun 2024cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 65 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

34 of 65 references.

References · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  4. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  5. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  6. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,818
  7. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  8. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
  9. 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 491
  10. 2019PAWS: Paraphrase Adversaries from Word Scramblingcited by 402
  11. 2021Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translationcited by 338
  12. 2017Six Challenges for Neural Machine Translationcited by 335
22 more
  1. 2016Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Modelscited by 301
  2. 2023xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detectioncited by 265
  3. 2024Tower: An Open Multilingual Large Language Model for Translation-Related Taskscited by 206
  4. 2019Facebook FAIR's WMT19 News Translation Task Submissioncited by 179
  5. 2020Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metricscited by 158
  6. 2020Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translationcited by 138
  7. 2018Analyzing Uncertainty in Neural Machine Translationcited by 126
  8. 2022Truncation Sampling as Language Model Desmoothingcited by 123
  9. 2018Correcting Length Bias in Neural Machine Translationcited by 120
  10. 2019On NMT Search Errors and Model Errors: Cat Got Your Tongue?cited by 114
  11. 2021High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metricscited by 104
  12. 2021Learning Compact Metrics for MTcited by 93
  13. 2023Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Taskcited by 88
  14. 2021Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translationcited by 65
  15. 2023Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translationcited by 58
  16. 2023Faster Minimum Bayes Risk Decoding with Confidence-based Pruningcited by 34
  17. 2016Neural Machine Translation with Reconstructioncited by 28
  18. 2023BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Trainingcited by 24
  19. 2024Linear-time Minimum Bayes Risk Decoding with Reference Aggregationcited by 21
  20. 2016Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Latticescited by 17
  21. 2024Centroid-Based Efficient Minimum Bayes Risk Decodingcited by 12
  22. 2017Later-stage Minimum Bayes-Risk Decoding for Neural Machine Translationcited by 8

Built on by

Not cited yet.