# Revisiting Adversarial Autoencoder for Unsupervised Word Translation with Cycle Consistency and Improved Training

arXiv: https://arxiv.org/abs/1904.04116 · HTML: https://mlsanity.com/paper/1904.04116/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2019.

## Built on by (most cited first, 12 of 12)

- [A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias](https://mlsanity.com/paper/2404.00929/) (2024)
- [Improving Word Translation via Two-Stage Contrastive Learning](https://mlsanity.com/paper/2203.08307/) (2022)
- [Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction](https://mlsanity.com/paper/2106.03084/) (2021)
- [So Different Yet So Alike! Constrained Unsupervised Text Style Transfer](https://mlsanity.com/paper/2205.04093/) (2022)
- [Quantized Wasserstein Procrustes Alignment of Word Embedding Spaces](https://mlsanity.com/paper/2212.02468/) (2022)
- [AUGVIC: Exploiting BiText Vicinity for Low-Resource NMT](https://mlsanity.com/paper/2106.05141/) (2021)
- [RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction](https://mlsanity.com/paper/2210.09926/) (2022)
- [Learning a Reversible Embedding Mapping using Bi-Directional Manifold Alignment](https://mlsanity.com/paper/2107.00124/) (2021)
- [LexGen: Domain-aware Multilingual Lexicon Generation](https://mlsanity.com/paper/2405.11200/) (2024)
- [Don't Forget Cheap Training Signals Before Building Unsupervised Bilingual Word Embeddings](https://mlsanity.com/paper/2205.15713/) (2022)
- [Robust Unsupervised Cross-Lingual Word Embedding using Domain Flow Interpolation](https://mlsanity.com/paper/2210.03319/) (2022)
- [Chem-FINESE: Validating Fine-Grained Few-shot Entity Extraction through Text Reconstruction](https://mlsanity.com/paper/2401.10189/) (2024)

## Abstract (arXiv)

Adversarial training has shown impressive success in learning bilingual dictionary without any parallel data by mapping monolingual embeddings to a shared space. However, recent work has shown superior performance for non-adversarial methods in more challenging language pairs. In this work, we revisit adversarial autoencoder for unsupervised word translation and propose two novel extensions to it that yield more stable training and improved results. Our method includes regularization terms to enforce cycle consistency and input reconstruction, and puts the target encoders as an adversary against the corresponding discriminator. Extensive experimentations with European, non-European and low-resource languages show that our method is more robust and achieves better performance than recently proposed adversarial and non-adversarial approaches.