# Unsupervised Neural Machine Translation with Weight Sharing

arXiv: https://arxiv.org/abs/1804.09057 · HTML: https://mlsanity.com/paper/1804.09057/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Apr 2018.

## Built on by (most cited first, 15 of 15)

- [Neural Machine Translation for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2106.15115/) (2021)
- [Harnessing the Universal Geometry of Embeddings](https://mlsanity.com/paper/2505.12540/) (2025)
- [A Survey on Low-Resource Neural Machine Translation](https://mlsanity.com/paper/2107.04239/) (2021)
- [Vashantor: A Large-scale Multilingual Benchmark Dataset for Automated Translation of Bangla Regional Dialects to Bangla Language](https://mlsanity.com/paper/2311.11142/) (2023)
- [Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning](https://mlsanity.com/paper/2407.01320/) (2024)
- [Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation](https://mlsanity.com/paper/2203.08394/) (2022)
- [Integrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languages](https://mlsanity.com/paper/2107.08772/) (2021)
- [Flow-Adapter Architecture for Unsupervised Machine Translation](https://mlsanity.com/paper/2204.12225/) (2022)
- [Crosslingual Embeddings are Essential in UNMT for Distant Languages: An English to IndoAryan Case Study](https://mlsanity.com/paper/2106.04995/) (2021)
- [Unsupervised Translation of Emergent Communication](https://mlsanity.com/paper/2502.07552/) (2025)
- [The Impact of Syntactic and Semantic Proximity on Machine Translation with Back-Translation](https://mlsanity.com/paper/2403.18031/) (2024)
- [Paraphrase Generation as Unsupervised Machine Translation](https://mlsanity.com/paper/2109.02950/) (2021)
- [Revisiting Implicit Models: Sparsity Trade-offs Capability in Weight-tied Model for Vision Tasks](https://mlsanity.com/paper/2307.08013/) (2023)
- [Generative-Adversarial Networks for Low-Resource Language Data Augmentation in Machine Translation](https://mlsanity.com/paper/2409.00071/) (2024)
- [Virtual neural networks: hundreds of souls in a body](https://mlsanity.com/paper/2609.24782/) (2026)

## Abstract (arXiv)

Unsupervised neural machine translation (NMT) is a recently proposed approach for machine translation which aims to train the model without using any labeled data. The models proposed for unsupervised NMT often use only one shared encoder to map the pairs of sentences from different languages to a shared-latent space, which is weak in keeping the unique and internal characteristics of each language, such as the style, terminology, and sentence structure. To address this issue, we introduce an extension by utilizing two independent encoders but sharing some partial weights which are responsible for extracting high-level representations of the input sentences. Besides, two different generative adversarial networks (GANs), namely the local GAN and global GAN, are proposed to enhance the cross-language translation. With this new approach, we achieve significant improvements on English-German, English-French and Chinese-to-English translation tasks.