# Neural Dynamic Focused Topic Model

arXiv: https://arxiv.org/abs/2301.10988 · HTML: https://mlsanity.com/paper/2301.10988/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 36 references that are in the map.
- First posted on arXiv 26 Jan 2023.

## Builds on (most cited first, 15 of 15)

- [Topic Modeling in Embedding Spaces](https://mlsanity.com/paper/1907.04907/) (2019)
- [Autoencoding Variational Inference For Topic Models](https://mlsanity.com/paper/1703.01488/) (2017)
- [Deep Kalman Filters](https://mlsanity.com/paper/1511.05121/) (2015)
- [Neural Variational Inference for Text Processing](https://mlsanity.com/paper/1511.06038/) (2015)
- [Discovering Discrete Latent Topics with Neural Variational Inference](https://mlsanity.com/paper/1706.00359/) (2017)
- [Dynamic Word Embeddings](https://mlsanity.com/paper/1702.08359/) (2017)
- [Neural Topic Model via Optimal Transport](https://mlsanity.com/paper/2008.13537/) (2020)
- [The Dynamic Embedded Topic Model](https://mlsanity.com/paper/1907.05545/) (2019)
- [WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling](https://mlsanity.com/paper/1803.01328/) (2018)
- [Understanding State Preferences With Text As Data: Introducing the UN General Debate Corpus](https://mlsanity.com/paper/1707.02774/) (2017)
- [Scalable Generalized Dynamic Topic Models](https://mlsanity.com/paper/1803.07868/) (2018)
- [A Discrete Variational Recurrent Topic Model without the Reparametrization Trick](https://mlsanity.com/paper/2010.12055/) (2020)
- [Poisson Random Fields for Dynamic Feature Models](https://mlsanity.com/paper/1611.07460/) (2016)
- [Word Network Topic Model: A Simple but General Solution for Short and Imbalanced Texts](https://mlsanity.com/paper/1412.5404/) (2014)
- [Dynamic and Static Topic Model for Analyzing Time-Series Document Collections](https://mlsanity.com/paper/1805.02203/) (2018)

## Built on by (most cited first, 8 of 8)

- [A Survey on Neural Topic Models: Methods, Applications, and Challenges](https://mlsanity.com/paper/2401.15351/) (2024)
- [In-Context Learning of Stochastic Differential Equations with Foundation Inference Models](https://mlsanity.com/paper/2502.19049/) (2025)
- [Dynamic Topic Evolution with Temporal Decay and Attention in Large Language Models](https://mlsanity.com/paper/2510.10613/) (2025)
- [Foundation Inference Models for Ordinary Differential Equations](https://mlsanity.com/paper/2602.08733/) (2026)
- [Towards Fast Coarse-graining and Equation Discovery with Foundation Inference Models](https://mlsanity.com/paper/2510.12618/) (2025)
- [Towards Foundation Inference Models that Learn ODEs In-Context](https://mlsanity.com/paper/2510.12650/) (2025)
- [Automating Historical Insight Extraction from Large-Scale Newspaper Archives via Neural Topic Modeling](https://mlsanity.com/paper/2512.11635/) (2025)
- [BERTilda: Explainable Topic Lifecycle Tracking with Split/Merge Detection via Similarity-and-Flow Temporal Graphs](https://mlsanity.com/paper/2608.18101/) (2026)

## Abstract (arXiv)

Topic models and all their variants analyse text by learning meaningful representations through word co-occurrences. As pointed out by Williamson et al. (2010), such models implicitly assume that the probability of a topic to be active and its proportion within each document are positively correlated. This correlation can be strongly detrimental in the case of documents created over time, simply because recent documents are likely better described by new and hence rare topics. In this work we leverage recent advances in neural variational inference and present an alternative neural approach to the dynamic Focused Topic Model. Indeed, we develop a neural model for topic evolution which exploits sequences of Bernoulli random variables in order to track the appearances of topics, thereby decoupling their activities from their proportions. We evaluate our model on three different datasets (the UN general debates, the collection of NeurIPS papers, and the ACL Anthology dataset) and show that it (i) outperforms state-of-the-art topic models in generalization tasks and (ii) performs comparably to them on prediction tasks, while employing roughly the same number of parameters, and converging about two times faster. Source code to reproduce our experiments is available online.