mlsanityData to 7 Oct 2026

Word Translation Without Parallel Data

arXiv 1710.04087 ↗First posted 11 Oct 2017cs.CLcited by 480

Not on the map. Why?

Abstract (arXiv)

State-of-the-art methods for learning cross-lingual word embeddings have relied on bilingual dictionaries or parallel corpora. Recent studies showed that the need for parallel data supervision can be alleviated with character-level information. While these methods showed encouraging results, they are not on par with their supervised counterparts and are limited to pairs of languages sharing a common alphabet. In this work, we show that we can build a bilingual dictionary between two languages without using any parallel corpora, by aligning monolingual word embedding spaces in an unsupervised way. Without using any character information, our model even outperforms existing supervised methods on cross-lingual tasks for some language pairs. Our experiments demonstrate that our method works very well also for distant language pairs, like English-Russian or English-Chinese. We finally describe experiments on the English-Esperanto low-resource language pair, on which there only exists a limited amount of parallel data, to show the potential impact of our method in fully unsupervised machine translation. Our code, embeddings and dictionaries are publicly available.

Key facts. Cited by 480 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 124; 2022: 92; 2023: 76; 2024: 74; 2025: 54; 2026: 60.

480 papers.

Sort:

By area:

  1. 2023The Linear Representation Hypothesis and the Geometry of Large Language Modelscited by 679
  2. 2022Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learningcited by 553
  3. 2022Language Models are Multilingual Chain-of-Thought Reasonerscited by 518
  4. 2023Function Vectors in Large Language Modelscited by 292
  5. 2022Self-Supervised Speech Representation Learning: A Reviewcited by 258
  6. 2023ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learningcited by 203
  7. 2022A Self-Supervised Descriptor for Image Copy Detectioncited by 175
  8. 2022Relative representations enable zero-shot latent space communicationcited by 175
  9. 2021Unsupervised Speech Recognitioncited by 147
  10. 2023Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Modelscited by 144
  11. 2021BERT: A Review of Applications in Natural Language Processing and Understandingcited by 109
  12. 2021Neural Machine Translation for Low-Resource Languages: A Surveycited by 108
38 more
  1. 2021Survey of Low-Resource Machine Translationcited by 92
  2. 2021WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language modelscited by 89
  3. 2021Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoderscited by 88
  4. 2024A Survey on Multilingual Large Language Models: Corpora, Alignment, and Biascited by 82
  5. 2021Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translationcited by 74
  6. 2023Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translationcited by 74
  7. 2021NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentationcited by 72
  8. 2021Cross Modal Retrieval with Querybank Normalisationcited by 71
  9. 2024The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalitiescited by 69
  10. 2021Towards generalisable hate speech detection: a review on obstacles and solutionscited by 66
  11. 2021Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costscited by 61
  12. 2022A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibilitycited by 61
  13. 2021Are Multilingual Models Effective in Code-Switching?cited by 56
  14. 2024ALLaM: Large Language Models for Arabic and Englishcited by 55
  15. 2021How to Adapt Your Pretrained Multilingual Model to 1600 Languagescited by 54
  16. 2025Harnessing the Universal Geometry of Embeddingscited by 54
  17. 2021AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languagescited by 50
  18. 2023Latent Space Translation via Semantic Alignmentcited by 46
  19. 2021Differentially Private Federated Knowledge Graphs Embeddingcited by 45
  20. 2021The 2021 Image Similarity Dataset and Challengecited by 44
  21. 2024Do Vision and Language Encoders Represent the World Similarly?cited by 44
  22. 2021MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NERcited by 42
  23. 2024MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modelingcited by 40
  24. 2023Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearningcited by 39
  25. 2023Black Box Few-Shot Adaptation for Vision-Language modelscited by 39
  26. 2021Boosting the Speed of Entity Alignment 10*: Dual Attention Matching Network with Normalized Hard Sample Miningcited by 37
  27. 2025Refusal Direction is Universal Across Safety-Aligned Languagescited by 37
  28. 2022GenHPF: General Healthcare Predictive Framework with Multi-task Multi-source Learningcited by 35
  29. 2022The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challengescited by 35
  30. 2024Understanding Cross-Lingual Alignment -- A Surveycited by 34
  31. 2021Multi-modal Sarcasm Detection and Humor Classification in Code-mixed Conversationscited by 33
  32. 2021Civil Rephrases Of Toxic Texts With Self-Supervised Transformerscited by 32
  33. 2021Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translationcited by 29
  34. 2021From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Textcited by 29
  35. 2024Teaching Large Language Models an Unseen Language on the Flycited by 29
  36. 2021Grounding Representation Similarity with Statistical Testingcited by 28
  37. 2021Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linkingcited by 27
  38. 2023Do Vision and Language Models Share Concepts? A Vector Space Alignment Studycited by 27

50 most cited of 480 All 480 (JSON)