# Dynamic Embedded Topic Models: properties and recommendations based on diverse corpora

arXiv: https://arxiv.org/abs/2504.19209 · HTML: https://mlsanity.com/paper/2504.19209/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 27 Apr 2025.

## Builds on (most cited first, 9 of 9)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Topic Modeling in Embedding Spaces](https://mlsanity.com/paper/1907.04907/) (2019)
- [Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence](https://mlsanity.com/paper/2107.02173/) (2021)
- [Efficient softmax approximation for GPUs](https://mlsanity.com/paper/1609.04309/) (2016)
- [The Dynamic Embedded Topic Model](https://mlsanity.com/paper/1907.05545/) (2019)
- [Augment and Reduce: Stochastic Inference for Large Categorical Distributions](https://mlsanity.com/paper/1802.04220/) (2018)
- [Computational modeling of semantic change](https://mlsanity.com/paper/2304.06337/) (2023)
- [Dynamic embedded topic models and change-point detection for exploring literary-historical hypotheses](https://mlsanity.com/paper/2401.13905/) (2024)
- [Anchor & Transform: Learning Sparse Embeddings for Large Vocabularies](https://mlsanity.com/paper/2003.08197/) (2020)

## Abstract (arXiv)

We measure the effects of several implementation choices for the Dynamic Embedded Topic Model, as applied to five distinct diachronic corpora, with the goal of isolating important decisions for its use and further development. We identify priorities that will maximize utility in applied scholarship, including the practical scalability of vocabulary size to best exploit the strengths of embedded representations, and more flexible modeling of intervals to accommodate the uneven temporal distributions of historical writing. Of similar importance, we find performance is not significantly or consistently affected by several aspects that otherwise limit the model's application or might consume the resources of a grid search.