# Analyzing the Limitations of Cross-lingual Word Embedding Mappings

arXiv: https://arxiv.org/abs/1906.05407 · HTML: https://mlsanity.com/paper/1906.05407/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2019.

## Built on by (most cited first, 19 of 19)

- [On the Theoretical Limitations of Embedding-Based Retrieval](https://mlsanity.com/paper/2508.21038/) (2025)
- [Understanding Cross-Lingual Alignment -- A Survey](https://mlsanity.com/paper/2404.06228/) (2024)
- [CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning](https://mlsanity.com/paper/2303.12793/) (2023)
- [Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention](https://mlsanity.com/paper/2410.12462/) (2024)
- [Subword Mapping and Anchoring across Languages](https://mlsanity.com/paper/2109.04556/) (2021)
- [Unsupervised Multilingual Sentence Embeddings for Parallel Corpus Mining](https://mlsanity.com/paper/2105.10419/) (2021)
- [Transferring Knowledge Distillation for Multilingual Social Event Detection](https://mlsanity.com/paper/2108.03084/) (2021)
- [IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces](https://mlsanity.com/paper/2210.05098/) (2022)
- [Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport](https://mlsanity.com/paper/2210.14378/) (2022)
- [Hubness Reduction Improves Sentence-BERT Semantic Spaces](https://mlsanity.com/paper/2311.18364/) (2023)
- [Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings](https://mlsanity.com/paper/2103.06459/) (2021)
- [Cross-lingual alignments of ELMo contextual embeddings](https://mlsanity.com/paper/2106.15986/) (2021)
- [An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces](https://mlsanity.com/paper/2109.12640/) (2021)
- [ProMap: Effective Bilingual Lexicon Induction via Language Model Prompting](https://mlsanity.com/paper/2310.18778/) (2023)
- [Isomorphic Cross-lingual Embeddings for Low-Resource Languages](https://mlsanity.com/paper/2203.14632/) (2022)
- [Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment](https://mlsanity.com/paper/2205.11616/) (2022)
- [How Lexical is Bilingual Lexicon Induction?](https://mlsanity.com/paper/2404.04221/) (2024)
- [Decipherment-Aware Multilingual Learning in Jointly Trained Language Models](https://mlsanity.com/paper/2406.07231/) (2024)
- [ROSETTA: Rotation Subspace Estimation for Training-free Transmodal Alignment](https://mlsanity.com/paper/2610.12871/) (2026)

## Abstract (arXiv)

Recent research in cross-lingual word embeddings has almost exclusively focused on offline methods, which independently train word embeddings in different languages and map them to a shared space through linear transformations. While several authors have questioned the underlying isomorphism assumption, which states that word embeddings in different languages have approximately the same structure, it is not clear whether this is an inherent limitation of mapping approaches or a more general issue when learning cross-lingual embeddings. So as to answer this question, we experiment with parallel corpora, which allows us to compare offline mapping to an extension of skip-gram that jointly learns both embedding spaces. We observe that, under these ideal conditions, joint learning yields to more isomorphic embeddings, is less sensitive to hubness, and obtains stronger results in bilingual lexicon induction. We thus conclude that current mapping methods do have strong limitations, calling for further research to jointly learn cross-lingual embeddings with a weaker cross-lingual signal.