# Unsupervised Hyperalignment for Multilingual Word Embeddings

arXiv: https://arxiv.org/abs/1811.01124 · HTML: https://mlsanity.com/paper/1811.01124/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2018.

## Built on by (most cited first, 17 of 17)

- [TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series](https://mlsanity.com/paper/2308.08241/) (2023)
- [Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs](https://mlsanity.com/paper/2106.01128/) (2021)
- [Hierarchical Multi-Marginal Optimal Transport for Network Alignment](https://mlsanity.com/paper/2310.04470/) (2023)
- [Cultural Compass: Predicting Transfer Learning Success in Offensive Language Detection with Cultural Features](https://mlsanity.com/paper/2310.06458/) (2023)
- [Efficient Approximation of Gromov-Wasserstein Distance Using Importance Sparsification](https://mlsanity.com/paper/2205.13573/) (2022)
- [Discrete Probabilistic Inverse Optimal Transport](https://mlsanity.com/paper/2112.09754/) (2021)
- [Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport](https://mlsanity.com/paper/2210.14378/) (2022)
- [Quantized Wasserstein Procrustes Alignment of Word Embedding Spaces](https://mlsanity.com/paper/2212.02468/) (2022)
- [Lens: Rethinking Multilingual Enhancement for Large Language Models](https://mlsanity.com/paper/2410.04407/) (2024)
- [Nearly Tight Convergence Bounds for Semi-discrete Entropic Optimal Transport](https://mlsanity.com/paper/2110.12678/) (2021)
- [Denoising Word Embeddings by Averaging in a Shared Space](https://mlsanity.com/paper/2106.02954/) (2021)
- [Algorithms for Weak Optimal Transport with an Application to Economics](https://mlsanity.com/paper/2205.09825/) (2022)
- [Don't Forget Cheap Training Signals Before Building Unsupervised Bilingual Word Embeddings](https://mlsanity.com/paper/2205.15713/) (2022)
- [Leveraging knowledge graphs to update scientific word embeddings using latent semantic imputation](https://mlsanity.com/paper/2210.15358/) (2022)
- [Towards Matching Phones and Speech Representations](https://mlsanity.com/paper/2310.17558/) (2023)
- [Covariance alignment: from maximum likelihood estimation to Gromov-Wasserstein](https://mlsanity.com/paper/2311.13595/) (2023)
- [Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment](https://mlsanity.com/paper/2205.11616/) (2022)

## Abstract (arXiv)

We consider the problem of aligning continuous word representations, learned in multiple languages, to a common space. It was recently shown that, in the case of two languages, it is possible to learn such a mapping without supervision. This paper extends this line of work to the problem of aligning multiple languages to a common space. A solution is to independently map all languages to a pivot language. Unfortunately, this degrades the quality of indirect word translation. We thus propose a novel formulation that ensures composable mappings, leading to better alignments. We evaluate our method by jointly aligning word vectors in eleven languages, showing consistent improvement with indirect mappings while maintaining competitive performance on direct word translation.