mlsanityData to 7 Oct 2026

Topic Modelling Meets Deep Neural Networks: A Survey

arXiv 2103.00498 ↗First posted 28 Feb 2021cs.LG cs.CL cs.IRcited by 51

Not on the map. Why?

Abstract (arXiv)

Topic modelling has been a successful technique for text analysis for almost twenty years. When topic modelling met deep neural networks, there emerged a new and increasingly popular research area, neural topic models, with over a hundred models developed and a wide range of applications in neural language understanding such as text generation, summarisation and language models. There is a need to summarise research developments and discuss open problems and future directions. In this paper, we provide a focused yet comprehensive overview of neural topic models for interested researchers in the AI community, so as to facilitate them to navigate and innovate in this fast-growing research area. To the best of our knowledge, ours is the first review focusing on this specific topic.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). Builds on 45 of its 85 references that are in the map. First posted on arXiv 28 Feb 2021.

Builds on

45 of 85 references.

References · 45

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2019Topic Modeling in Embedding Spacescited by 224
  3. 2017Autoencoding Variational Inference For Topic Modelscited by 168
  4. 2020Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherencecited by 121
  5. 2015Neural Variational Inference for Text Processingcited by 111
  6. 2017Discovering Discrete Latent Topics with Neural Variational Inferencecited by 79
  7. 2019Topic Modeling with Wasserstein Autoencoderscited by 53
  8. 2020Neural Topic Model via Optimal Transportcited by 50
  9. 2017Neural Models for Documents with Metadatacited by 46
  10. 2016Stick-Breaking Variational Autoencoderscited by 44
  11. 2019Topic-Guided Variational Autoencoders for Text Generationcited by 44
  12. 2019Dirichlet Variational Autoencodercited by 43
33 more
  1. 2020Topic Modeling with Contextualized Word Representation Clusterscited by 41
  2. 2018WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modelingcited by 32
  3. 2016The Generalized Reparameterization Gradientcited by 30
  4. 2020Neural Topic Modeling with Bidirectional Adversarial Trainingcited by 29
  5. 2018Improving Topic Models with Latent Feature Word Representationscited by 28
  6. 2016TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependencycited by 27
  7. 2018Coherence-Aware Neural Topic Modelingcited by 26
  8. 2018Topic Memory Networks for Short Text Classificationcited by 25
  9. 2020Improving Neural Topic Models using Knowledge Distillationcited by 25
  10. 2020Neural Topic Modeling with Continual Lifelong Learningcited by 24
  11. 2018ATM:Adversarial-neural Topic Modelcited by 23
  12. 2016Reparameterization Gradients through Acceptance-Rejection Sampling Algorithmscited by 22
  13. 2020Enhancing Extractive Text Summarization with Topic-Aware Graph Neural Networkscited by 22
  14. 2015Gamma Belief Networkscited by 19
  15. 2020Neural Topic Modeling by Incorporating Document Relationship Graphcited by 13
  16. 2018Dirichlet belief networks for topic structure learningcited by 12
  17. 2020Neural Topic Modeling with Cycle-Consistent Adversarial Trainingcited by 12
  18. 2017Topic Compositional Neural Language Modelcited by 11
  19. 2018Document Informed Neural Autoregressive Topic Models with Distributional Priorcited by 11
  20. 2020Context Reinforced Neural Topic Modeling over Short Textscited by 10
  21. 2020TAN-NTM: Topic Attention Networks for Neural Topic Modelingcited by 10
  22. 2018Sparsemax and Relaxed Wasserstein for Topic Sparsitycited by 9
  23. 2020A Discrete Variational Recurrent Topic Model without the Reparametrization Trickcited by 9
  24. 2017Topically Driven Neural Language Modelcited by 8
  25. 2020TopicBERT for Energy Efficient Document Classificationcited by 8
  26. 2017MetaLDA: a Topic Model that Efficiently Incorporates Meta informationcited by 6
  27. 2017KATE: K-Competitive Autoencoder for Textcited by 5
  28. 2018textTOvec: Deep Contextualized Neural Autoregressive Topic Models of Language with Distributed Compositional Priorcited by 5
  29. 2018Dirichlet Variational Autoencoder for Text Modelingcited by 5
  30. 2017SenGen: Sentence Generating Neural Variational Topic Modelcited by 4
  31. 2018Nonparametric Topic Modeling with Neural Inferencecited by 3
  32. 2019Discriminative Topic Modeling with Logistic LDAcited by 3
  33. 2017Continuous Semantic Topic Embedding Model Using Variational Autoencodercited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 10; 2023: 16; 2024: 11; 2025: 8; 2026: 2.

51 papers.

Sort:

By area:

  1. 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 779
  2. 2021Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherencecited by 74
  3. 2023Effective Neural Topic Modeling with Embedding Clustering Regularizationcited by 46
  4. 2022Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddingscited by 36
  5. 2022Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topicscited by 35
  6. 2024FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Modelcited by 34
  7. 2021Sawtooth Factorial Topic Embeddings Guided Gamma Belief Networkcited by 23
  8. 2023Towards the TopMost: A Topic Modeling System Toolkitcited by 21
  9. 2023Contextualized Topic Coherence Metricscited by 19
  10. 2024A Survey on Neural Topic Models: Methods, Applications, and Challengescited by 18
  11. 2024German Text Embedding Clustering Benchmarkcited by 13
  12. 2022Are Neural Topic Models Broken?cited by 11
38 more
  1. 2024LLM Reading Tea Leaves: Automatically Evaluating Topic Models with Large Language Modelscited by 11
  2. 2022Challenges and Opportunities in Information Manipulation Detection: An Examination of Wartime Russian Mediacited by 10
  3. 2024Neural Topic Modeling with Large Language Models in the Loopcited by 10
  4. 2024Automatic Histograms: Leveraging Language Models for Text Dataset Explorationcited by 8
  5. 2024Semantic-Driven Topic Modeling Using Transformer-Based Embeddings and Clustering Algorithmscited by 8
  6. 2021Neural Attention-Aware Hierarchical Topic Modelcited by 6
  7. 2024Neural Multimodal Topic Modeling: A Comprehensive Evaluationcited by 5
  8. 2023Improving Contextualized Topic Models with Negative Samplingcited by 4
  9. 2023The Elements of Visual Art Recommendation: Learning Latent Semantic Representations of Paintingscited by 3
  10. 2023Do Neural Topic Models Really Need Dropout? Analysis of the Effect of Dropout in Topic Modelingcited by 3
  11. 2021Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioningcited by 2
  12. 2022No Pattern, No Recognition: a Survey about Reproducibility and Distortion Issues of Text Clustering and Topic Modelingcited by 2
  13. 2023PheME: A deep ensemble framework for improving phenotype prediction from multi-modal datacited by 2
  14. 2024Topic Modeling with Fine-tuning LLMs and Bag of Sentencescited by 2
  15. 2025Semantic-Driven Topic Modeling for Analyzing Creativity in Virtual Brainstormingcited by 2
  16. 2025Importance-aware Topic Modeling for Discovering Public Transit Risk from Noisy Social Mediacited by 2
  17. 2022Adversarial Learned Fair Representations using Dampening and Stackingcited by 1
  18. 2023Topics in Contextualised Attention Embeddingscited by 1
  19. 2023Efficient and Flexible Topic Modeling using Pretrained Embeddings and Bag of Sentencescited by 1
  20. 2023Reinforcement Learning for Topic Modelscited by 1
  21. 2023Parameter Estimation in DAGs from Incomplete Data via Optimal Transportcited by 1
  22. 2023Towards Generalising Neural Topical Representationscited by 1
  23. 2023MixEHR-SurG: a joint proportional hazard and guided topic model for inferring mortality-associated topics from electronic health recordscited by 1
  24. 2024Distilled ChatGPT Topic & Sentiment Modeling with Applications in Financecited by 1
  25. 2025Recommending the right academic programs: An interest mining approach using BERTopiccited by 1
  26. 2025SciTopic: Enhancing Topic Discovery in Scientific Literature through Advanced LLMcited by 1
  27. 2026Structuring the Space of Perspectivescited by 1
  28. 2022One Configuration to Rule Them All? Towards Hyperparameter Transfer in Topic Models using Multi-Objective Bayesian Optimizationcited by 0
  29. 2022A Comparison of Approaches for Imbalanced Classification Problems in the Context of Retrieving Relevant Documents for an Analysiscited by 0
  30. 2022Learning Semantic Textual Similarity via Topic-informed Discrete Latent Variablescited by 0
  31. 2023Graph2topic: an opensource topic modeling framework based on sentence embedding and community detectioncited by 0
  32. 2023Deep Dive into the Language of International Relations: NLP-based Analysis of UNESCO's Summary Recordscited by 0
  33. 2023What are Public Concerns about ChatGPT? A Novel Self-Supervised Neural Topic Model Tells Youcited by 0
  34. 2024Semantic Component Analysis: Introducing Multi-Topic Distributions to Clustering-Based Topic Modelingcited by 0
  35. 2025Self-Supervised Learning for Neural Topic Models with Variance-Invariance-Covariance Regularizationcited by 0
  36. 2025Constrained Non-negative Matrix Factorization for Guided Topic Modeling of Minority Topicscited by 0
  37. 2025Agentic Retrieval of Topics and Insights from Earnings Callscited by 0
  38. 2025TopiCLEAR: Adaptive embedding clustering for interpretable topic discovery from short textscited by 0

50 most cited of 51 All 51 (JSON)