# Improving Cross-Lingual Word Embeddings by Meeting in the Middle

arXiv: https://arxiv.org/abs/1808.08780 · HTML: https://mlsanity.com/paper/1808.08780/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2018.

## Built on by (most cited first, 13 of 13)

- [A Survey on Word Meta-Embedding Learning](https://mlsanity.com/paper/2204.11660/) (2022)
- [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)
- [Harnessing Cross-lingual Features to Improve Cognate Detection for Low-resource Languages](https://mlsanity.com/paper/2112.08789/) (2021)
- [Cross-lingual Transferring of Pre-trained Contextualized Language Models](https://mlsanity.com/paper/2107.12627/) (2021)
- [Cognition-aware Cognate Detection](https://mlsanity.com/paper/2112.08087/) (2021)
- [GARI: Graph Attention for Relative Isomorphism of Arabic Word Embeddings](https://mlsanity.com/paper/2310.13068/) (2023)
- [An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces](https://mlsanity.com/paper/2109.12640/) (2021)
- [Cross-Lingual Phrase Retrieval](https://mlsanity.com/paper/2204.08887/) (2022)
- [Robust Unsupervised Cross-Lingual Word Embedding using Domain Flow Interpolation](https://mlsanity.com/paper/2210.03319/) (2022)
- [Distilling Monolingual and Crosslingual Word-in-Context Representations](https://mlsanity.com/paper/2409.08719/) (2024)
- [How Good is BLI as an Alignment Measure: A Study in Word Embedding Paradigm](https://mlsanity.com/paper/2511.13040/) (2025)
- [Embedding Initialization for Unseen Low-resource Languages in Multilingual NMT: A Case Study on Limbum-English Translation](https://mlsanity.com/paper/2608.07629/) (2026)

## Abstract (arXiv)

Cross-lingual word embeddings are becoming increasingly important in multilingual NLP. Recently, it has been shown that these embeddings can be effectively learned by aligning two disjoint monolingual vector spaces through linear transformations, using no more than a small bilingual dictionary as supervision. In this work, we propose to apply an additional transformation after the initial alignment step, which moves cross-lingual synonyms towards a middle point between them. By applying this transformation our aim is to obtain a better cross-lingual integration of the vector spaces. In addition, and perhaps surprisingly, the monolingual spaces also improve by this transformation. This is in contrast to the original alignment, which is typically learned such that the structure of the monolingual spaces is preserved. Our experiments confirm that the resulting cross-lingual embeddings outperform state-of-the-art models in both monolingual and cross-lingual evaluation tasks.