# Unsupervised Natural Language Generation with Denoising Autoencoders

arXiv: https://arxiv.org/abs/1804.07899 · HTML: https://mlsanity.com/paper/1804.07899/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2018.

## Built on by (most cited first, 9 of 9)

- [SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption](https://mlsanity.com/paper/2106.15147/) (2021)
- [Neural Data-to-Text Generation with LM-based Text Augmentation](https://mlsanity.com/paper/2102.03556/) (2021)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [A Systematic Review of Data-to-Text NLG](https://mlsanity.com/paper/2402.08496/) (2024)
- [SparseGAN: Sparse Generative Adversarial Network for Text Generation](https://mlsanity.com/paper/2103.11578/) (2021)
- [Data Augmentation for Voice-Assistant NLU using BERT-based Interchangeable Rephrase](https://mlsanity.com/paper/2104.08268/) (2021)
- [Natural Language Generation Using Link Grammar for General Conversational Intelligence](https://mlsanity.com/paper/2105.00830/) (2021)
- [Data-efficient Performance Modeling via Pre-training](https://mlsanity.com/paper/2501.14438/) (2025)
- [TextEconomizer: Enhancing Lossy Text Compression with Denoising Transformers and Entropy Coding](https://mlsanity.com/paper/2606.08184/) (2026)

## Abstract (arXiv)

Generating text from structured data is important for various tasks such as question answering and dialog systems. We show that in at least one domain, without any supervision and only based on unlabeled text, we are able to build a Natural Language Generation (NLG) system with higher performance than supervised approaches. In our approach, we interpret the structured data as a corrupt representation of the desired output and use a denoising auto-encoder to reconstruct the sentence. We show how to introduce noise into training examples that do not contain structured data, and that the resulting denoising auto-encoder generalizes to generate correct sentences when given structured data.