# Multi-Adversarial Learning for Cross-Lingual Word Embeddings

arXiv: https://arxiv.org/abs/2010.08432 · HTML: https://mlsanity.com/paper/2010.08432/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2020.

## Built on by (most cited first, 7 of 7)

- [A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias](https://mlsanity.com/paper/2404.00929/) (2024)
- [How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?](https://mlsanity.com/paper/2109.01100/) (2021)
- [Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport](https://mlsanity.com/paper/2210.14378/) (2022)
- [SexWEs: Domain-Aware Word Embeddings via Cross-lingual Semantic Specialisation for Chinese Sexism Detection in Social Media](https://mlsanity.com/paper/2211.08447/) (2022)
- [TokAlign++: Advancing Vocabulary Adaptation via Better Token Alignment](https://mlsanity.com/paper/2605.13429/) (2026)
- [Epi-Curriculum: Episodic Curriculum Learning for Low-Resource Domain Adaptation in Neural Machine Translation](https://mlsanity.com/paper/2309.02640/) (2023)
- [A survey of neural-network-based methods utilising comparable data for finding translation equivalents](https://mlsanity.com/paper/2410.15144/) (2024)

## Abstract (arXiv)

Generative adversarial networks (GANs) have succeeded in inducing cross-lingual word embeddings -- maps of matching words across languages -- without supervision. Despite these successes, GANs' performance for the difficult case of distant languages is still not satisfactory. These limitations have been explained by GANs' incorrect assumption that source and target embedding spaces are related by a single linear mapping and are approximately isomorphic. We assume instead that, especially across distant languages, the mapping is only piece-wise linear, and propose a multi-adversarial learning method. This novel method induces the seed cross-lingual dictionary through multiple mappings, each induced to fit the mapping for one subspace. Our experiments on unsupervised bilingual lexicon induction show that this method improves performance over previous single-mapping methods, especially for distant languages.