# From Unsupervised Machine Translation To Adversarial Text Generation

arXiv: https://arxiv.org/abs/2011.05449 · HTML: https://mlsanity.com/paper/2011.05449/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Nov 2020.

## Built on by (most cited first, 1 of 1)

- [Breaking Down the Task: A Unit-Grained Hybrid Training Framework for Vision and Language Decision Making](https://mlsanity.com/paper/2307.08016/) (2023)

## Abstract (arXiv)

We present a self-attention based bilingual adversarial text generator (B-GAN) which can learn to generate text from the encoder representation of an unsupervised neural machine translation system. B-GAN is able to generate a distributed latent space representation which can be paired with an attention based decoder to generate fluent sentences. When trained on an encoder shared between two languages and paired with the appropriate decoder, it can generate sentences in either language. B-GAN is trained using a combination of reconstruction loss for auto-encoder, a cross domain loss for translation and a GAN based adversarial loss for text generation. We demonstrate that B-GAN, trained on monolingual corpora only using multiple losses, generates more fluent sentences compared to monolingual baselines while effectively using half the number of parameters.