mlsanityData to 7 Oct 2026

Improving Back-Translation with Uncertainty-based Confidence Estimation

arXiv 1909.00157 ↗First posted 31 Aug 2019cs.CLcited by 34

Not on the map. Why?

Abstract (arXiv)

While back-translation is simple and effective in exploiting abundant monolingual corpora to improve low-resource neural machine translation (NMT), the synthetic bilingual corpora generated by NMT models trained on limited authentic bilingual data are inevitably noisy. In this work, we propose to quantify the confidence of NMT model predictions based on model uncertainty. With word- and sentence-level confidence measures based on uncertainty, it is possible for back-translation to better cope with noise in synthetic bilingual corpora. Experiments on Chinese-English and English-German translation tasks show that uncertainty-based confidence estimation significantly improves the performance of back-translation.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 13; 2022: 6; 2023: 8; 2024: 6; 2025: 1.

34 papers.

Sort:

  1. 2024Language Model Cascades: Token-level uncertainty and beyondcited by 115
  2. 2021Neural Machine Translation for Low-Resource Languages: A Surveycited by 108
  3. 2021Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Taskscited by 100
  4. 2024Calibrating Large Language Models Using Their Generations Onlycited by 63
  5. 2023Uncertainty in Natural Language Processing: Sources, Quantification, and Applicationscited by 44
  6. 2021Uncertainty-Aware Machine Translation Evaluationcited by 35
  7. 2021Prevent the Language Model from being Overconfident in Neural Machine Translationcited by 34
  8. 2023On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Studycited by 25
  9. 2021A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applicationscited by 24
  10. 2021Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Trainingcited by 19
  11. 2021Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translationcited by 17
  12. 2021On the Complementarity between Pre-Training and Back-Translation for Neural Machine Translationcited by 14
22 more
  1. 2021Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correctioncited by 11
  2. 2022Calibration of Machine Reading Systems at Scalecited by 11
  3. 2021Confidence-Aware Scheduled Sampling for Neural Machine Translationcited by 10
  4. 2021Trust It or Not: Confidence-Guided Automatic Radiology Report Generationcited by 9
  5. 2022SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parserscited by 7
  6. 2023Uncertainty-Aware Bootstrap Learning for Joint Extraction on Distantly-Supervised Datacited by 7
  7. 2021Exploiting Curriculum Learning in Unsupervised Neural Machine Translationcited by 6
  8. 2023Active Learning for Abstractive Text Summarizationcited by 6
  9. 2022Training Dynamics for Curriculum Learning: A Study on Monolingual and Cross-lingual NLUcited by 5
  10. 2024Self-Modifying State Modeling for Simultaneous Machine Translationcited by 5
  11. 2023On Synthetic Data for Back Translationcited by 4
  12. 2021Alternated Training with Synthetic and Authentic Data for Neural Machine Translationcited by 3
  13. 2024Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization?cited by 3
  14. 2022RMBR: A Regularized Minimum Bayes Risk Reranking Framework for Machine Translationcited by 2
  15. 2022Learning Confidence for Transformer-based Neural Machine Translationcited by 2
  16. 2022Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality?cited by 2
  17. 2023Perception and Semantic Aware Regularization for Sequential Confidence Calibrationcited by 1
  18. 2023CBSiMT: Mitigating Hallucination in Simultaneous Machine Translation with Weighted Prefix-to-Prefix Trainingcited by 1
  19. 2023DA3: A Distribution-Aware Adversarial Attack against Language Modelscited by 1
  20. 2024An Effective Incorporating Heterogeneous Knowledge Curriculum Learning for Sequence Labelingcited by 1
  21. 2024Multi-Evidence based Fact Verification via A Confidential Graph Neural Networkcited by 1
  22. 2025Monocle: Hybrid Local-Global In-Context Evaluation for Long-Text Generation with Uncertainty-Based Active Learningcited by 1