mlsanityData to 7 Oct 2026

An Effective Approach to Unsupervised Machine Translation

arXiv 1902.01313 ↗First posted 4 Feb 2019cs.CL cs.AI cs.LGcited by 37

Not on the map. Why?

Abstract (arXiv)

While machine translation has traditionally relied on large amounts of parallel corpora, a recent research line has managed to train both Neural Machine Translation (NMT) and Statistical Machine Translation (SMT) systems using monolingual corpora only. In this paper, we identify and address several deficiencies of existing unsupervised SMT approaches by exploiting subword information, developing a theoretically well founded unsupervised tuning method, and incorporating a joint refinement procedure. Moreover, we use our improved SMT system to initialize a dual NMT model, which is further fine-tuned through on-the-fly back-translation. Together, we obtain large improvements over the previous state-of-the-art in unsupervised machine translation. For instance, we get 22.5 BLEU points in English-to-German WMT 2014, 5.5 points more than the previous best unsupervised system, and 0.5 points more than the (supervised) shared task winner back in 2014.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 8; 2023: 9; 2024: 3; 2025: 1; 2026: 2.

37 papers.

Sort:

  1. 2021Neural Machine Translation for Low-Resource Languages: A Surveycited by 108
  2. 2023SLaDe: A Portable Small Language Model Decompiler for Optimized Assemblycited by 28
  3. 2021Multilingual Unsupervised Neural Machine Translation with Denoising Adapterscited by 22
  4. 2022Modeling Dual Read/Write Paths for Simultaneous Machine Translationcited by 21
  5. 2021A Survey on Low-Resource Neural Machine Translationcited by 16
  6. 2022USCORE: An Effective Approach to Fully Unsupervised Evaluation Metrics for Machine Translationcited by 15
  7. 2021Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translationcited by 14
  8. 2023Bilex Rx: Lexical Data Augmentation for Massively Multilingual Machine Translationcited by 7
  9. 2023Unsupervised Melody-to-Lyric Generationcited by 7
  10. 2022Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transportcited by 6
  11. 2021Majority Voting with Bidirectional Pre-translation For Bitext Retrievalcited by 5
  12. 2022Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translationcited by 5
25 more
  1. 2023Translating away Translationese without Parallel Datacited by 5
  2. 2021On Systematic Style Differences between Unsupervised and Supervised MT and an Application for High-Resource Machine Translationcited by 4
  3. 2021Integrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languagescited by 4
  4. 2021"A Passage to India": Pre-trained Word Embeddings for Indian Languagescited by 4
  5. 2021Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languagescited by 3
  6. 2022Multilingual Bidirectional Unsupervised Translation Through Multilingual Finetuning and Back-Translationcited by 3
  7. 2023Align before Search: Aligning Ads Image to Text for Accurate Cross-Modal Sponsored Searchcited by 3
  8. 2021An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spacescited by 2
  9. 2022Exploiting Social Media Content for Self-Supervised Style Transfercited by 2
  10. 2022A Semi-supervised Approach for a Better Translation of Sentiment in Dialectical Arabic UGTcited by 2
  11. 2023Text Attribute Control via Closed-Loop Disentanglementcited by 2
  12. 2025Towards Unsupervised Speech Recognition at the Syllable-Levelcited by 2
  13. 2021Unsupervised Transfer Learning in Multilingual Neural Machine Translation with Cross-Lingual Word Embeddingscited by 1
  14. 2022Domain Mismatch Doesn't Always Prevent Cross-Lingual Transfer Learningcited by 1
  15. 2024Effective Self-Mining of In-Context Examples for Unsupervised Machine Translation with LLMscited by 1
  16. 2021Embedding-Enhanced Giza++: Improving Alignment in Low- and High- Resource Scenarios Using Embedding Space Geometrycited by 0
  17. 2021Icelandic Parallel Abstracts Corpuscited by 0
  18. 2021Paraphrase Generation as Unsupervised Machine Translationcited by 0
  19. 2023Boosting Unsupervised Machine Translation with Pseudo-Parallel Datacited by 0
  20. 2023Relevance-guided Neural Machine Translationcited by 0
  21. 2023An Empirical study of Unsupervised Neural Machine Translation: analyzing NMT output, model's behavior and sentences' contributioncited by 0
  22. 2024Decoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languagescited by 0
  23. 2024A survey of neural-network-based methods utilising comparable data for finding translation equivalentscited by 0
  24. 2026Unsupervised Cross-Lingual Part-of-Speech Tagging with Monolingual Corpora Onlycited by 0
  25. 2026Ensemble Self-Training for Unsupervised Machine Translationcited by 0