# Unsupervised Multilingual Word Embeddings

arXiv: https://arxiv.org/abs/1808.08933 · HTML: https://mlsanity.com/paper/1808.08933/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2018.

## Built on by (most cited first, 16 of 16)

- [mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset](https://mlsanity.com/paper/2108.13897/) (2021)
- [Harnessing the Universal Geometry of Embeddings](https://mlsanity.com/paper/2505.12540/) (2025)
- [Hyperpolyglot LLMs: Cross-Lingual Interpretability in Token Embeddings](https://mlsanity.com/paper/2311.18034/) (2023)
- [Conceptual similarity and communicative need shape colexification: an experimental study](https://mlsanity.com/paper/2103.11024/) (2021)
- [Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation](https://mlsanity.com/paper/2109.04653/) (2021)
- [mini-vec2vec: Scaling Universal Geometry Alignment with Linear Transformations](https://mlsanity.com/paper/2510.02348/) (2025)
- [Denoising Word Embeddings by Averaging in a Shared Space](https://mlsanity.com/paper/2106.02954/) (2021)
- [XNLI 2.0: Improving XNLI dataset and performance on Cross Lingual Understanding (XLU)](https://mlsanity.com/paper/2301.06527/) (2023)
- [Don't Forget Cheap Training Signals Before Building Unsupervised Bilingual Word Embeddings](https://mlsanity.com/paper/2205.15713/) (2022)
- [Multilingual Word Embeddings for Low-Resource Languages using Anchors and a Chain of Related Languages](https://mlsanity.com/paper/2311.12489/) (2023)
- [Priberam Labs at the NTCIR-15 SHINRA2020-ML: Classification Task](https://mlsanity.com/paper/2105.05605/) (2021)
- [Cross-language Information Retrieval](https://mlsanity.com/paper/2111.05988/) (2021)
- [BITS Pilani at HinglishEval: Quality Evaluation for Code-Mixed Hinglish Text Using Transformers](https://mlsanity.com/paper/2206.08680/) (2022)
- [Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning](https://mlsanity.com/paper/2505.13628/) (2025)
- [Advancing credit mobility through stakeholder-informed AI design and adoption](https://mlsanity.com/paper/2601.05666/) (2026)
- [Comparison of Modern Multilingual Text Embedding Techniques for Hate Speech Detection Task](https://mlsanity.com/paper/2604.14907/) (2026)

## Abstract (arXiv)

Multilingual Word Embeddings (MWEs) represent words from multiple languages in a single distributional vector space. Unsupervised MWE (UMWE) methods acquire multilingual embeddings without cross-lingual supervision, which is a significant advantage over traditional supervised approaches and opens many new possibilities for low-resource languages. Prior art for learning UMWEs, however, merely relies on a number of independently trained Unsupervised Bilingual Word Embeddings (UBWEs) to obtain multilingual embeddings. These methods fail to leverage the interdependencies that exist among many languages. To address this shortcoming, we propose a fully unsupervised framework for learning MWEs that directly exploits the relations between all language pairs. Our model substantially outperforms previous approaches in the experiments on multilingual word translation and cross-lingual word similarity. In addition, our model even beats supervised approaches trained with cross-lingual resources.