# Generative Neural Machine Translation

arXiv: https://arxiv.org/abs/1806.05138 · HTML: https://mlsanity.com/paper/1806.05138/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2018.

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

- [Transformer-based Conditional Variational Autoencoder for Controllable Story Generation](https://mlsanity.com/paper/2101.00828/) (2021)
- [Language Models are Good Translators](https://mlsanity.com/paper/2106.13627/) (2021)
- [QiMeng-Xpiler: Transcompiling Tensor Programs for Deep Learning Systems with a Neural-Symbolic Approach](https://mlsanity.com/paper/2505.02146/) (2025)
- [Improving Variational Autoencoders with Density Gap-based Regularization](https://mlsanity.com/paper/2211.00321/) (2022)
- [Rapid Review of Generative AI in Smart Medical Applications](https://mlsanity.com/paper/2406.06627/) (2024)
- [Recurrence Boosts Diversity! Revisiting Recurrent Latent Variable in Transformer-Based Variational AutoEncoder for Diverse Text Generation](https://mlsanity.com/paper/2210.12409/) (2022)
- [Shared Latent Space by Both Languages in Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/2305.03511/) (2023)

## Abstract (arXiv)

We introduce Generative Neural Machine Translation (GNMT), a latent variable architecture which is designed to model the semantics of the source and target sentences. We modify an encoder-decoder translation model by adding a latent variable as a language agnostic representation which is encouraged to learn the meaning of the sentence. GNMT achieves competitive BLEU scores on pure translation tasks, and is superior when there are missing words in the source sentence. We augment the model to facilitate multilingual translation and semi-supervised learning without adding parameters. This framework significantly reduces overfitting when there is limited paired data available, and is effective for translating between pairs of languages not seen during training.