# A Discrete Variational Recurrent Topic Model without the Reparametrization Trick

arXiv: https://arxiv.org/abs/2010.12055 · HTML: https://mlsanity.com/paper/2010.12055/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2020.

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

- [Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence](https://mlsanity.com/paper/2107.02173/) (2021)
- [Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection](https://mlsanity.com/paper/2106.01071/) (2021)
- [Topic Modelling Meets Deep Neural Networks: A Survey](https://mlsanity.com/paper/2103.00498/) (2021)
- [A Survey on Neural Topic Models: Methods, Applications, and Challenges](https://mlsanity.com/paper/2401.15351/) (2024)
- [Neural Dynamic Focused Topic Model](https://mlsanity.com/paper/2301.10988/) (2023)
- [Interpretable Fake News Detection with Topic and Deep Variational Models](https://mlsanity.com/paper/2209.01536/) (2022)
- [Revisiting Topic-Guided Language Models](https://mlsanity.com/paper/2312.02331/) (2023)
- [Sparse Universum Quadratic Surface Support Vector Machine Models for Binary Classification](https://mlsanity.com/paper/2104.01331/) (2021)
- [An Overview on Controllable Text Generation via Variational Auto-Encoders](https://mlsanity.com/paper/2211.07954/) (2022)

## Abstract (arXiv)

We show how to learn a neural topic model with discrete random variables---one that explicitly models each word's assigned topic---using neural variational inference that does not rely on stochastic backpropagation to handle the discrete variables. The model we utilize combines the expressive power of neural methods for representing sequences of text with the topic model's ability to capture global, thematic coherence. Using neural variational inference, we show improved perplexity and document understanding across multiple corpora. We examine the effect of prior parameters both on the model and variational parameters and demonstrate how our approach can compete and surpass a popular topic model implementation on an automatic measure of topic quality.