mlsanityData to 7 Oct 2026

Are All Good Word Vector Spaces Isomorphic?

arXiv 2004.04070 ↗First posted 8 Apr 2020cs.CLcited by 36

Not on the map. Why?

Abstract (arXiv)

Existing algorithms for aligning cross-lingual word vector spaces assume that vector spaces are approximately isomorphic. As a result, they perform poorly or fail completely on non-isomorphic spaces. Such non-isomorphism has been hypothesised to result from typological differences between languages. In this work, we ask whether non-isomorphism is also crucially a sign of degenerate word vector spaces. We present a series of experiments across diverse languages which show that variance in performance across language pairs is not only due to typological differences, but can mostly be attributed to the size of the monolingual resources available, and to the properties and duration of monolingual training (e.g. "under-training").

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 7; 2023: 6; 2024: 12; 2025: 2; 2026: 1.

36 papers.

Sort:

  1. 2022Relative representations enable zero-shot latent space communicationcited by 175
  2. 2023Latent Space Translation via Semantic Alignmentcited by 46
  3. 2024Do Vision and Language Encoders Represent the World Similarly?cited by 44
  4. 2024Understanding Cross-Lingual Alignment -- A Surveycited by 34
  5. 2021An Isotropy Analysis in the Multilingual BERT Embedding Spacecited by 25
  6. 2021Obtaining Better Static Word Embeddings Using Contextual Embedding Modelscited by 18
  7. 2021Do Language Models Know the Way to Rome?cited by 18
  8. 2024Latent Space Translation via Inverse Relative Projectioncited by 10
  9. 2021A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Spacecited by 8
  10. 2022Combining Static and Contextualised Multilingual Embeddingscited by 8
  11. 2022IsoVec: Controlling the Relative Isomorphism of Word Embedding Spacescited by 7
  12. 2023Bootstrapping Parallel Anchors for Relative Representationscited by 7
24 more
  1. 2023Neural Machine Translation for the Indigenous Languages of the Americas: An Introductioncited by 7
  2. 2024GrEmLIn: A Repository of Green Baseline Embeddings for 87 Low-Resource Languages Injected with Multilingual Graph Knowledgecited by 7
  3. 2021Cross-Lingual BERT Contextual Embedding Space Mapping with Isotropic and Isometric Conditionscited by 6
  4. 2022Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transportcited by 6
  5. 2023Are Structural Concepts Universal in Transformer Language Models? Towards Interpretable Cross-Lingual Generalizationcited by 6
  6. 2025Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spacescited by 6
  7. 2021Majority Voting with Bidirectional Pre-translation For Bitext Retrievalcited by 5
  8. 2024Survey in Characterizing Semantic Changecited by 5
  9. 2024The Shape of Word Embeddings: Quantifying Non-Isometry With Topological Data Analysiscited by 4
  10. 2024Relative Representations: Topological and Geometric Perspectivescited by 4
  11. 2024MoSECroT: Model Stitching with Static Word Embeddings for Crosslingual Zero-shot Transfercited by 2
  12. 2024FedAnchor: Enhancing Federated Semi-Supervised Learning with Label Contrastive Loss for Unlabeled Clientscited by 2
  13. 2024A Comprehensive Analysis of Static Word Embeddings for Turkishcited by 2
  14. 2024Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignmentcited by 2
  15. 2021Examining Cross-lingual Contextual Embeddings with Orthogonal Structural Probescited by 1
  16. 2022Isomorphic Cross-lingual Embeddings for Low-Resource Languagescited by 1
  17. 2023Linguistically-Informed Neural Architectures for Lexical, Syntactic and Semantic Tasks in Sanskritcited by 1
  18. 2023Large language models converge toward human-like concept organizationcited by 1
  19. 2024Latent Functional Maps: a spectral framework for representation alignmentcited by 1
  20. 2021Do Multi-Lingual Pre-trained Language Models Reveal Consistent Token Attributions in Different Languages?cited by 0
  21. 2022Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignmentcited by 0
  22. 2022Efficient Entity Candidate Generation for Low-Resource Languagescited by 0
  23. 2025Benchmarking Cross-Lingual Semantic Alignment in Multilingual Embeddingscited by 0
  24. 2026Effective vocabulary expansion of multilingual language models for extremely low-resource languagescited by 0