# Dirichlet Variational Autoencoder for Text Modeling

arXiv: https://arxiv.org/abs/1811.00135 · HTML: https://mlsanity.com/paper/1811.00135/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2018.

## Built on by (most cited first, 5 of 5)

- [Topic Modelling Meets Deep Neural Networks: A Survey](https://mlsanity.com/paper/2103.00498/) (2021)
- [AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language Modeling](https://mlsanity.com/paper/2205.05862/) (2022)
- [Improving Variational Autoencoder based Out-of-Distribution Detection for Embedded Real-time Applications](https://mlsanity.com/paper/2107.11750/) (2021)
- [Physics-informed Variational Autoencoders for Improved Robustness to Environmental Factors of Variation](https://mlsanity.com/paper/2210.10418/) (2022)
- [An Overview on Controllable Text Generation via Variational Auto-Encoders](https://mlsanity.com/paper/2211.07954/) (2022)

## Abstract (arXiv)

We introduce an improved variational autoencoder (VAE) for text modeling with topic information explicitly modeled as a Dirichlet latent variable. By providing the proposed model topic awareness, it is more superior at reconstructing input texts. Furthermore, due to the inherent interactions between the newly introduced Dirichlet variable and the conventional multivariate Gaussian variable, the model is less prone to KL divergence vanishing. We derive the variational lower bound for the new model and conduct experiments on four different data sets. The results show that the proposed model is superior at text reconstruction across the latent space and classifications on learned representations have higher test accuracies.