mlsanityData to 7 Oct 2026

Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport

arXiv 2210.14378 ↗First posted 25 Oct 2022cs.CL cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Bilingual lexicons form a critical component of various natural language processing applications, including unsupervised and semisupervised machine translation and crosslingual information retrieval. We improve bilingual lexicon induction performance across 40 language pairs with a graph-matching method based on optimal transport. The method is especially strong with low amounts of supervision.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 39 of its 59 references that are in the map. First posted on arXiv 25 Oct 2022.

Builds on

39 of 59 references.

References · 39

  1. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  2. 2016Enriching Word Vectors with Subword Informationcited by 1,578
  3. 2018Computational Optimal Transportcited by 765
  4. 2017Word Translation Without Parallel Datacited by 480
  5. 2013Exploiting Similarities among Languages for Machine Translationcited by 187
  6. 2018A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddingscited by 145
  7. 2018Gromov-Wasserstein Alignment of Word Embedding Spacescited by 119
  8. 2018Unsupervised Alignment of Embeddings with Wasserstein Procrustescited by 96
  9. 2018Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterioncited by 69
  10. 2018On the Limitations of Unsupervised Bilingual Dictionary Inductioncited by 61
  11. 2019How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptionscited by 48
  12. 2018FRAGE: Frequency-Agnostic Word Representationcited by 47
27 more
  1. 2020When Does Unsupervised Machine Translation Work?cited by 38
  2. 2019An Effective Approach to Unsupervised Machine Translationcited by 37
  3. 2020A Call for More Rigor in Unsupervised Cross-lingual Learningcited by 37
  4. 2020Are All Good Word Vector Spaces Isomorphic?cited by 36
  5. 2019Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spacescited by 35
  6. 2019Do We Really Need Fully Unsupervised Cross-Lingual Embeddings?cited by 31
  7. 2020Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Modelcited by 24
  8. 2021Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word Alignmentcited by 19
  9. 2019Analyzing the Limitations of Cross-lingual Word Embedding Mappingscited by 18
  10. 2018Unsupervised Hyperalignment for Multilingual Word Embeddingscited by 17
  11. 2018Unsupervised Cross-lingual Transfer of Word Embedding Spacescited by 16
  12. 2019Bilingual Lexicon Induction through Unsupervised Machine Translationcited by 16
  13. 2019GraSPy: Graph Statistics in Pythoncited by 15
  14. 2019Are Girls Neko or Sh=ojo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalizationcited by 15
  15. 2019Don't Forget the Long Tail! A Comprehensive Analysis of Morphological Generalization in Bilingual Lexicon Inductioncited by 15
  16. 2018Improving Cross-Lingual Word Embeddings by Meeting in the Middlecited by 13
  17. 2018A Discriminative Latent-Variable Model for Bilingual Lexicon Inductioncited by 8
  18. 2020A Relaxed Matching Procedure for Unsupervised BLIcited by 8
  19. 2017Unsupervised Word Mapping Using Structural Similarities in Monolingual Embeddingscited by 7
  20. 2018Characterizing Departures from Linearity in Word Translationcited by 7
  21. 2020Why Overfitting Isn't Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionariescited by 7
  22. 2020Multi-Adversarial Learning for Cross-Lingual Word Embeddingscited by 7
  23. 2020On a Novel Application of Wasserstein-Procrustes for Unsupervised Cross-Lingual Learningcited by 6
  24. 2021Graph Matching via Optimal Transportcited by 6
  25. 2021Learning a Reversible Embedding Mapping using Bi-Directional Manifold Alignmentcited by 2
  26. 2021An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spacescited by 2
  27. 2020Refinement of Unsupervised Cross-Lingual Word Embeddingscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 2; 2025: 1.

6 papers.

  1. 2024The Zeno's Paradox of `Low-Resource' Languagescited by 12
  2. 2023Optimal Transport Posterior Alignment for Cross-lingual Semantic Parsingcited by 2
  3. 2023ProMap: Effective Bilingual Lexicon Induction via Language Model Promptingcited by 2
  4. 2023Accessing Higher Dimensions for Unsupervised Word Translationcited by 0
  5. 2024A survey of neural-network-based methods utilising comparable data for finding translation equivalentscited by 0
  6. 2025Asymptotically perfect seeded graph matching without edge correlation (and applications to inference)cited by 0