# Towards cross-lingual distributed representations without parallel text trained with adversarial autoencoders

arXiv: https://arxiv.org/abs/1608.02996 · HTML: https://mlsanity.com/paper/1608.02996/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2016.

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

- [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022)
- [Hyperpolyglot LLMs: Cross-Lingual Interpretability in Token Embeddings](https://mlsanity.com/paper/2311.18034/) (2023)
- [IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces](https://mlsanity.com/paper/2210.05098/) (2022)
- [Cross-Lingual BERT Contextual Embedding Space Mapping with Isotropic and Isometric Conditions](https://mlsanity.com/paper/2107.09186/) (2021)
- [A Theory of Unsupervised Translation Motivated by Understanding Animal Communication](https://mlsanity.com/paper/2211.11081/) (2022)
- [Quantized Wasserstein Procrustes Alignment of Word Embedding Spaces](https://mlsanity.com/paper/2212.02468/) (2022)
- [The Shape of Word Embeddings: Quantifying Non-Isometry With Topological Data Analysis](https://mlsanity.com/paper/2404.00500/) (2024)
- [Sub-Word Alignment Is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translation](https://mlsanity.com/paper/2205.04067/) (2022)
- [High-Dimensional Interlingual Representations of Large Language Models](https://mlsanity.com/paper/2503.11280/) (2025)
- [Robust Unsupervised Cross-Lingual Word Embedding using Domain Flow Interpolation](https://mlsanity.com/paper/2210.03319/) (2022)
- [Zero-Resource Multi-Dialectal Arabic Natural Language Understanding](https://mlsanity.com/paper/2104.06591/) (2021)
- [Unsupervised Alignment of Distributional Word Embeddings](https://mlsanity.com/paper/2203.04863/) (2022)
- [Decipherment-Aware Multilingual Learning in Jointly Trained Language Models](https://mlsanity.com/paper/2406.07231/) (2024)

## Abstract (arXiv)

Current approaches to learning vector representations of text that are compatible between different languages usually require some amount of parallel text, aligned at word, sentence or at least document level. We hypothesize however, that different natural languages share enough semantic structure that it should be possible, in principle, to learn compatible vector representations just by analyzing the monolingual distribution of words. In order to evaluate this hypothesis, we propose a scheme to map word vectors trained on a source language to vectors semantically compatible with word vectors trained on a target language using an adversarial autoencoder. We present preliminary qualitative results and discuss possible future developments of this technique, such as applications to cross-lingual sentence representations.