# Coherence-Aware Neural Topic Modeling

arXiv: https://arxiv.org/abs/1809.02687 · HTML: https://mlsanity.com/paper/1809.02687/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Sep 2018.

## Built on by (most cited first, 26 of 26)

- [Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence](https://mlsanity.com/paper/2107.02173/) (2021)
- [Topic Modelling Meets Deep Neural Networks: A Survey](https://mlsanity.com/paper/2103.00498/) (2021)
- [Contrastive Learning for Neural Topic Model](https://mlsanity.com/paper/2110.12764/) (2021)
- [Enriching and Controlling Global Semantics for Text Summarization](https://mlsanity.com/paper/2109.10616/) (2021)
- [Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modeling](https://mlsanity.com/paper/2104.05064/) (2021)
- [CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modeling](https://mlsanity.com/paper/2305.09329/) (2023)
- [Neural Attention-Aware Hierarchical Topic Model](https://mlsanity.com/paper/2110.07161/) (2021)
- [Diversity-Aware Coherence Loss for Improving Neural Topic Models](https://mlsanity.com/paper/2305.16199/) (2023)
- [Neural Multimodal Topic Modeling: A Comprehensive Evaluation](https://mlsanity.com/paper/2403.17308/) (2024)
- [Bridging the Evaluation Gap: Leveraging Large Language Models for Topic Model Evaluation](https://mlsanity.com/paper/2502.07352/) (2025)
- [Toward Purpose-oriented Topic Model Evaluation enabled by Large Language Models](https://mlsanity.com/paper/2509.07142/) (2025)
- [SocialVisTUM: An Interactive Visualization Toolkit for Correlated Neural Topic Models on Social Media Opinion Mining](https://mlsanity.com/paper/2110.10575/) (2021)
- [Enhance Topics Analysis based on Keywords Properties](https://mlsanity.com/paper/2203.04786/) (2022)
- [Neural Topic Modeling with Deep Mutual Information Estimation](https://mlsanity.com/paper/2203.06298/) (2022)
- [Towards Better Understanding with Uniformity and Explicit Regularization of Embeddings in Embedding-based Neural Topic Models](https://mlsanity.com/paper/2206.07960/) (2022)
- [ProSiT! Latent Variable Discovery with PROgressive SImilarity Thresholds](https://mlsanity.com/paper/2210.14763/) (2022)
- [You Are What You Talk About: Inducing Evaluative Topics for Personality Analysis](https://mlsanity.com/paper/2302.00493/) (2023)
- [FATRER: Full-Attention Topic Regularizer for Accurate and Robust Conversational Emotion Recognition](https://mlsanity.com/paper/2307.12221/) (2023)
- [Enhancing Topic Interpretability for Neural Topic Modeling through Topic-wise Contrastive Learning](https://mlsanity.com/paper/2412.17338/) (2024)
- [DiffETM: Diffusion Process Enhanced Embedded Topic Model](https://mlsanity.com/paper/2501.00862/) (2025)
- [One Configuration to Rule Them All? Towards Hyperparameter Transfer in Topic Models using Multi-Objective Bayesian Optimization](https://mlsanity.com/paper/2202.07631/) (2022)
- [Anchor Prediction: A Topic Modeling Approach](https://mlsanity.com/paper/2205.14631/) (2022)
- [Explainable Topic-Enhanced Argument Mining from Heterogeneous Sources](https://mlsanity.com/paper/2307.12131/) (2023)
- [Classification-Aware Neural Topic Model Combined With Interpretable Analysis -- For Conflict Classification](https://mlsanity.com/paper/2308.15232/) (2023)
- [Meta-probabilistic Modeling](https://mlsanity.com/paper/2601.04462/) (2026)
- [Hybrid Classical-Quantum Variational Autoencoder for Neural Topic Modeling](https://mlsanity.com/paper/2606.13852/) (2026)

## Abstract (arXiv)

Topic models are evaluated based on their ability to describe documents well (i.e. low perplexity) and to produce topics that carry coherent semantic meaning. In topic modeling so far, perplexity is a direct optimization target. However, topic coherence, owing to its challenging computation, is not optimized for and is only evaluated after training. In this work, under a neural variational inference framework, we propose methods to incorporate a topic coherence objective into the training process. We demonstrate that such a coherence-aware topic model exhibits a similar level of perplexity as baseline models but achieves substantially higher topic coherence.