mlsanityData to 14 Oct 2026

A Survey on Neural Topic Models: Methods, Applications, and Challenges

arXiv 2401.15351 ↗First posted 27 Jan 2024cs.CL cs.AI cs.IRcited by 18

Not on the map. Why?

Abstract (arXiv)

Topic models have been prevalent for decades to discover latent topics and infer topic proportions of documents in an unsupervised fashion. They have been widely used in various applications like text analysis and context recommendation. Recently, the rise of neural networks has facilitated the emergence of a new research field -- Neural Topic Models (NTMs). Different from conventional topic models, NTMs directly optimize parameters without requiring model-specific derivations. This endows NTMs with better scalability and flexibility, resulting in significant research attention and plentiful new methods and applications. In this paper, we present a comprehensive survey on neural topic models concerning methods, applications, and challenges. Specifically, we systematically organize current NTM methods according to their network structures and introduce the NTMs for various scenarios like short texts and bilingual documents. We also discuss a wide range of popular applications built on NTMs. Finally, we highlight the challenges confronted by NTMs to inspire future research. We accompany this survey with a repository for easier access to the mentioned paper resources: https://github.com/bobxwu/Paper-Neural-Topic-Models.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 61 of its 165 references that are in the map. First posted on arXiv 27 Jan 2024.

Builds on

61 of 165 references.

References · 61

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2017Neural Discrete Representation Learningcited by 4,712
  6. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  7. 2016Pointer Sentinel Mixture Modelscited by 3,096
  8. 2016Variational Inference: A Review for Statisticianscited by 1,472
  9. 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 801
  10. 2014Distributed Representations of Sentences and Documentscited by 678
  11. 2019Topic Modeling in Embedding Spacescited by 224
  12. 2017Autoencoding Variational Inference For Topic Modelscited by 169
38 more
  1. 2023Fact-Checking Complex Claims with Program-Guided Reasoningcited by 146
  2. 2020Top2Vec: Distributed Representations of Topicscited by 126
  3. 2020Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherencecited by 121
  4. 2015Neural Variational Inference for Text Processingcited by 111
  5. 2017Discovering Discrete Latent Topics with Neural Variational Inferencecited by 79
  6. 2021Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherencecited by 74
  7. 2020Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too!cited by 73
  8. 2020Cross-lingual Contextualized Topic Models with Zero-shot Learningcited by 67
  9. 2019Topic Modeling with Wasserstein Autoencoderscited by 53
  10. 2021Topic Modelling Meets Deep Neural Networks: A Surveycited by 51
  11. 2020Neural Topic Model via Optimal Transportcited by 50
  12. 2021Contrastive Learning for Neural Topic Modelcited by 48
  13. 2017Neural Models for Documents with Metadatacited by 46
  14. 2023Effective Neural Topic Modeling with Embedding Clustering Regularizationcited by 46
  15. 2019Dirichlet Variational Autoencodercited by 43
  16. 2019The Dynamic Embedded Topic Modelcited by 41
  17. 2020Topic Modeling with Contextualized Word Representation Clusterscited by 41
  18. 2019Short Text Topic Modeling Techniques, Applications, and Performance: A Surveycited by 38
  19. 2022Mitigating Data Sparsity for Short Text Topic Modeling by Topic-Semantic Contrastive Learningcited by 38
  20. 2022Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddingscited by 36
  21. 2022Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topicscited by 35
  22. 2018WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modelingcited by 32
  23. 2020Neural Topic Modeling with Bidirectional Adversarial Trainingcited by 29
  24. 2016TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependencycited by 27
  25. 2018Topic Memory Networks for Short Text Classificationcited by 25
  26. 2020Improving Neural Topic Models using Knowledge Distillationcited by 25
  27. 2020Neural Topic Modeling with Continual Lifelong Learningcited by 24
  28. 2023InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modelingcited by 24
  29. 2018ATM:Adversarial-neural Topic Modelcited by 23
  30. 2021Sawtooth Factorial Topic Embeddings Guided Gamma Belief Networkcited by 23
  31. 2023Towards the TopMost: A Topic Modeling System Toolkitcited by 21
  32. 2021Enriching and Controlling Global Semantics for Text Summarizationcited by 20
  33. 2024On the Affinity, Rationality, and Diversity of Hierarchical Topic Modelingcited by 18
  34. 2022HyperMiner: Topic Taxonomy Mining with Hyperbolic Embeddingcited by 15
  35. 2020Neural Topic Modeling by Incorporating Document Relationship Graphcited by 13
  36. 2020Neural Topic Modeling with Cycle-Consistent Adversarial Trainingcited by 12
  37. 2018Document Informed Neural Autoregressive Topic Models with Distributional Priorcited by 11
  38. 2018Sparsemax and Relaxed Wasserstein for Topic Sparsitycited by 9

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 14; 2026: 1.

18 papers.

Sort:

By area:

  1. 2024FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Modelcited by 35
  2. 2024Topic Modeling as Multi-Objective Contrastive Optimizationcited by 12
  3. 2025Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generationcited by 3
  4. 2025Sparse Autoencoders are Topic Modelscited by 3
  5. 2025Importance-aware Topic Modeling for Discovering Public Transit Risk from Noisy Social Mediacited by 2
  6. 2025Poisson-Process Topic Model for Integrating Knowledge from Pre-trained Language Modelscited by 1
  7. 2025Merging Embedded Topics with Optimal Transport for Online Topic Modeling on Data Streamscited by 1
  8. 2025E-LDA: Toward Interpretable LDA Topic Models with Strong Guarantees in Logarithmic Parallel Timecited by 1
  9. 2025Discourse-Aware Scientific Paper Recommendation via QA-Style Summarization and Multi-Level Contrastive Learningcited by 1
  10. 2024Hierarchical mixtures of Unigram models for short text clustering: The role of Beta-Liouville priorscited by 0
  11. 2025pytopicgram: A library for data extraction and topic modeling from Telegram channelscited by 0
  12. 2025Self-Supervised Learning for Neural Topic Models with Variance-Invariance-Covariance Regularizationcited by 0
6 more
  1. 2025Automated Bug Report Prioritization in Large Open-Source Projectscited by 0
  2. 2025Towards an automatic method for generating topical vocabulary test forms for specific reading passagescited by 0
  3. 2025scE2TM improves single-cell embedding interpretability and reveals cellular perturbation signaturescited by 0
  4. 2025Mapping Scientific Literature with Large Language Models and Topic Modelingcited by 0
  5. 2025From the Rock Floor to the Cloud: A Systematic Survey of State-of-the-Art NLP in Battery Life Cyclecited by 0
  6. 2026Population-level measures of perceived food access reveal barriers beyond geographic proximitycited by 0