mlsanityData to 7 Oct 2026

Unsupervised Statistical Machine Translation

arXiv 1809.01272 ↗First posted 4 Sep 2018cs.CL cs.AI cs.LGcited by 51

Not on the map. Why?

Abstract (arXiv)

While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al., 2018). Despite the potential of this approach for low-resource settings, existing systems are far behind their supervised counterparts, limiting their practical interest. In this paper, we propose an alternative approach based on phrase-based Statistical Machine Translation (SMT) that significantly closes the gap with supervised systems. Our method profits from the modular architecture of SMT: we first induce a phrase table from monolingual corpora through cross-lingual embedding mappings, combine it with an n-gram language model, and fine-tune hyperparameters through an unsupervised MERT variant. In addition, iterative backtranslation improves results further, yielding, for instance, 14.08 and 26.22 BLEU points in WMT 2014 English-German and English-French, respectively, an improvement of more than 7-10 BLEU points over previous unsupervised systems, and closing the gap with supervised SMT (Moses trained on Europarl) down to 2-5 BLEU points. Our implementation is available at https://github.com/artetxem/monoses

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 8; 2023: 8; 2024: 5; 2025: 5; 2026: 3.

51 papers.

Sort:

By area:

  1. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 556
  2. 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
  3. 2021Break-It-Fix-It: Unsupervised Learning for Program Repaircited by 71
  4. 2022Code Translation with Compiler Representationscited by 42
  5. 2023Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Reviewcited by 32
  6. 2022Inducing Positive Perspectives with Text Reframingcited by 31
  7. 2024RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translationcited by 21
  8. 2025Encoder-Decoder Diffusion Language Models for Efficient Training and Inferencecited by 21
  9. 2021Semi-Supervised Graph-to-Graph Translationcited by 18
  10. 2021Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translationcited by 14
  11. 2021An Unsupervised Method for Building Sentence Simplification Corpora in Multiple Languagescited by 14
  12. 2021Automatic Intent-Slot Induction for Dialogue Systemscited by 13
38 more
  1. 2022Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languagescited by 12
  2. 2024Graphusion: A RAG Framework for Knowledge Graph Construction with a Global Perspectivecited by 12
  3. 2021Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoderscited by 11
  4. 2021Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrievalcited by 8
  5. 2021Extremely low-resource machine translation for closely related languagescited by 7
  6. 2022MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generationcited by 7
  7. 2021Majority Voting with Bidirectional Pre-translation For Bitext Retrievalcited by 5
  8. 2021"Wikily" Supervised Neural Translation Tailored to Cross-Lingual Taskscited by 5
  9. 2023Translating away Translationese without Parallel Datacited by 5
  10. 2021Cross-lingual hate speech detection based on multilingual domain-specific word embeddingscited by 4
  11. 2021"A Passage to India": Pre-trained Word Embeddings for Indian Languagescited by 4
  12. 2021Sentence Alignment with Parallel Documents Facilitates Biomedical Machine Translationcited by 3
  13. 2021Crosslingual Embeddings are Essential in UNMT for Distant Languages: An English to IndoAryan Case Studycited by 3
  14. 2021HintedBT: Augmenting Back-Translation with Quality and Transliteration Hintscited by 3
  15. 2021Efficient Variational Graph Autoencoders for Unsupervised Cross-domain Prerequisite Chainscited by 3
  16. 2022Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Underdocumented Languagescited by 2
  17. 2022Computational Sarcasm Analysis on Social Media: A Systematic Reviewcited by 2
  18. 2023Text Attribute Control via Closed-Loop Disentanglementcited by 2
  19. 2025The Paradox of Poetic Intent in Back-Translation: Evaluating the Quality of Large Language Models in Chinese Translationcited by 2
  20. 2025Towards Unsupervised Speech Recognition at the Syllable-Levelcited by 2
  21. 2021Monolingual and Parallel Corpora for Kangri Low Resource Languagecited by 1
  22. 2024Effective Self-Mining of In-Context Examples for Unsupervised Machine Translation with LLMscited by 1
  23. 2025TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translationcited by 1
  24. 2026Aladdin-FTI @ AMIYA Three Wishes for Arabic NLP: Fidelity, Diglossia, and Multidialectal Generationcited by 1
  25. 2021Bilingual Terminology Extraction from Comparable E-Commerce Corporacited by 0
  26. 2021Paraphrase Generation as Unsupervised Machine Translationcited by 0
  27. 2021CLICKER: A Computational LInguistics Classification Scheme for Educational Resourcescited by 0
  28. 2022From meaning to perception -- exploring the space between word and odor perception embeddingscited by 0
  29. 2022Finding the Right Recipe for Low Resource Domain Adaptation in Neural Machine Translationcited by 0
  30. 2023Attention Link: An Efficient Attention-Based Low Resource Machine Translation Architecturecited by 0
  31. 2023Denoising-based UNMT is more robust to word-order divergence than MASS-based UNMTcited by 0
  32. 2023Sentence Simplification Using Paraphrase Corpus for Initializationcited by 0
  33. 2023Boosting Unsupervised Machine Translation with Pseudo-Parallel Datacited by 0
  34. 2023Quick Back-Translation for Unsupervised Machine Translationcited by 0
  35. 2024Decipherment-Aware Multilingual Learning in Jointly Trained Language Modelscited by 0
  36. 2024Decoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languagescited by 0
  37. 2025LLM-BT-Terms: Back-Translation as a Framework for Terminology Standardization and Dynamic Semantic Embeddingcited by 0
  38. 2026Leveraging Sentence-oriented Augmentation and Transformer-Based Architecture for Vietnamese-Bahnaric Translationcited by 0

50 most cited of 51 All 51 (JSON)