mlsanityData to 7 Oct 2026

A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings

arXiv 1805.06297 ↗First posted 16 May 2018cs.CL cs.AI cs.LGcited by 145

Not on the map. Why?

Abstract (arXiv)

Recent work has managed to learn cross-lingual word embeddings without parallel data by mapping monolingual embeddings to a shared space through adversarial training. However, their evaluation has focused on favorable conditions, using comparable corpora or closely-related languages, and we show that they often fail in more realistic scenarios. This work proposes an alternative approach based on a fully unsupervised initialization that explicitly exploits the structural similarity of the embeddings, and a robust self-learning algorithm that iteratively improves this solution. Our method succeeds in all tested scenarios and obtains the best published results in standard datasets, even surpassing previous supervised systems. Our implementation is released as an open source project at https://github.com/artetxem/vecmap

Key facts. Cited by 145 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 47; 2022: 33; 2023: 24; 2024: 17; 2025: 13; 2026: 11.

145 papers.

Sort:

By area:

  1. 2022Self-Supervised Speech Representation Learning: A Reviewcited by 258
  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. 2022NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languagescited by 67
  6. 2025Harnessing the Universal Geometry of Embeddingscited by 54
  7. 2023Black Box Few-Shot Adaptation for Vision-Language modelscited by 39
  8. 2021A Systematic Review of Reproducibility Research in Natural Language Processingcited by 34
  9. 2023CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learningcited by 32
  10. 2024PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoningcited by 31
  11. 2021HinGE: A Dataset for Generation and Evaluation of Code-Mixed Hinglish Textcited by 28
  12. 2023Do Vision and Language Models Share Concepts? A Vector Space Alignment Studycited by 27
38 more
  1. 2022ASR2K: Speech Recognition for Around 2000 Languages without Audiocited by 26
  2. 2023Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learnercited by 23
  3. 2021On Cross-Lingual Retrieval with Multilingual Text Encoderscited by 22
  4. 2021Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corporacited by 21
  5. 2021Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word Alignmentcited by 19
  6. 2023Discovering Universal Geometry in Embeddings with ICAcited by 19
  7. 2023Hyperpolyglot LLMs: Cross-Lingual Interpretability in Token Embeddingscited by 19
  8. 2022Improving Word Translation via Two-Stage Contrastive Learningcited by 18
  9. 2022Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbingcited by 17
  10. 2023Rethinking Semi-supervised Learning with Language Modelscited by 17
  11. 2021Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrievalcited by 16
  12. 2021Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systemscited by 16
  13. 2021A Survey on Low-Resource Neural Machine Translationcited by 16
  14. 2023TADA: Task-Agnostic Dialect Adapters for Englishcited by 15
  15. 2023SLABERT Talk Pretty One Day: Modeling Second Language Acquisition with BERTcited by 15
  16. 2021Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translationcited by 14
  17. 2024Optimizing Language Augmentation for Multilingual Large Language Models: A Case Study on Koreancited by 14
  18. 2025With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide Youcited by 13
  19. 2021Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Inductioncited by 12
  20. 2021Subword Mapping and Anchoring across Languagescited by 12
  21. 2021Prix-LM: Pretraining for Multilingual Knowledge Base Constructioncited by 12
  22. 2023Translatotron 3: Speech to Speech Translation with Monolingual Datacited by 12
  23. 2023Crosslingual Transfer Learning for Low-Resource Languages Based on Multilingual Colexification Graphscited by 11
  24. 2024Graph-based Clustering for Detecting Semantic Change Across Time and Languagescited by 10
  25. 2021Unsupervised Multilingual Sentence Embeddings for Parallel Corpus Miningcited by 9
  26. 2022Shapley Head Pruning: Identifying and Removing Interference in Multilingual Transformerscited by 9
  27. 2021Bootstrapping Multilingual AMR with Contextual Word Alignmentscited by 8
  28. 2022Towards a Broad Coverage Named Entity Resource: A Data-Efficient Approach for Many Diverse Languagescited by 8
  29. 2022Combining Static and Contextualised Multilingual Embeddingscited by 8
  30. 2021MIPE: A Metric Independent Pipeline for Effective Code-Mixed NLG Evaluationcited by 7
  31. 2021Transferring Knowledge Distillation for Multilingual Social Event Detectioncited by 7
  32. 2021Are the Multilingual Models Better? Improving Czech Sentiment with Transformerscited by 7
  33. 2022Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognitioncited by 7
  34. 2022Probing Cross-Lingual Lexical Knowledge from Multilingual Sentence Encoderscited by 7
  35. 2022Direct Speech Translation for Automatic Subtitlingcited by 7
  36. 2022IsoVec: Controlling the Relative Isomorphism of Word Embedding Spacescited by 7
  37. 2022Improving Bilingual Lexicon Induction with Cross-Encoder Rerankingcited by 7
  38. 2023Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language Modelscited by 7

50 most cited of 145 All 145 (JSON)