# A Joint Learning Approach for Semi-supervised Neural Topic Modeling

arXiv: https://arxiv.org/abs/2204.03208 · HTML: https://mlsanity.com/paper/2204.03208/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 38 references that are in the map.
- First posted on arXiv 7 Apr 2022.

## Builds on (most cited first, 12 of 12)

- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [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)
- [Neural Variational Inference for Text Processing](https://mlsanity.com/paper/1511.06038/) (2015)
- [Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence](https://mlsanity.com/paper/2107.02173/) (2021)
- [Topic Modeling with Wasserstein Autoencoders](https://mlsanity.com/paper/1907.12374/) (2019)
- [The Dynamic Embedded Topic Model](https://mlsanity.com/paper/1907.05545/) (2019)
- [Variational Tempering](https://mlsanity.com/paper/1411.1810/) (2014)
- [Few-shot Learning for Topic Modeling](https://mlsanity.com/paper/2104.09011/) (2021)
- [Prediction Focused Topic Models via Feature Selection](https://mlsanity.com/paper/1910.05495/) (2019)
- [On Learning Prediction-Focused Mixtures](https://mlsanity.com/paper/2110.13221/) (2021)

## Built on by (most cited first, 3 of 3)

- [vONTSS: vMF based semi-supervised neural topic modeling with optimal transport](https://mlsanity.com/paper/2307.01226/) (2023)
- [Aspect-Based Sentiment Analysis for Open-Ended HR Survey Responses](https://mlsanity.com/paper/2402.04812/) (2024)
- [Label Semantic Expansion via Label Guided Neural Topic Modeling](https://mlsanity.com/paper/2608.30216/) (2026)

## Abstract (arXiv)

Topic models are some of the most popular ways to represent textual data in an interpret-able manner. Recently, advances in deep generative models, specifically auto-encoding variational Bayes (AEVB), have led to the introduction of unsupervised neural topic models, which leverage deep generative models as opposed to traditional statistics-based topic models. We extend upon these neural topic models by introducing the Label-Indexed Neural Topic Model (LI-NTM), which is, to the extent of our knowledge, the first effective upstream semi-supervised neural topic model. We find that LI-NTM outperforms existing neural topic models in document reconstruction benchmarks, with the most notable results in low labeled data regimes and for data-sets with informative labels; furthermore, our jointly learned classifier outperforms baseline classifiers in ablation studies.