mlsanityData to 7 Oct 2026

Topic Modeling with Wasserstein Autoencoders

arXiv 1907.12374 ↗First posted 24 Jul 2019cs.IR cs.AI cs.LGcited by 53

Not on the map. Why?

Abstract (arXiv)

We propose a novel neural topic model in the Wasserstein autoencoders (WAE) framework. Unlike existing variational autoencoder based models, we directly enforce Dirichlet prior on the latent document-topic vectors. We exploit the structure of the latent space and apply a suitable kernel in minimizing the Maximum Mean Discrepancy (MMD) to perform distribution matching. We discover that MMD performs much better than the Generative Adversarial Network (GAN) in matching high dimensional Dirichlet distribution. We further discover that incorporating randomness in the encoder output during training leads to significantly more coherent topics. To measure the diversity of the produced topics, we propose a simple topic uniqueness metric. Together with the widely used coherence measure NPMI, we offer a more wholistic evaluation of topic quality. Experiments on several real datasets show that our model produces significantly better topics than existing topic models.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 12; 2023: 15; 2024: 7; 2025: 8; 2026: 4.

53 papers.

Sort:

  1. 2021Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherencecited by 74
  2. 2021Topic Modelling Meets Deep Neural Networks: A Surveycited by 51
  3. 2021Contrastive Learning for Neural Topic Modelcited by 48
  4. 2023Effective Neural Topic Modeling with Embedding Clustering Regularizationcited by 46
  5. 2022Mitigating Data Sparsity for Short Text Topic Modeling by Topic-Semantic Contrastive Learningcited by 38
  6. 2022Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddingscited by 36
  7. 2022Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topicscited by 35
  8. 2023InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modelingcited by 24
  9. 2021Sawtooth Factorial Topic Embeddings Guided Gamma Belief Networkcited by 23
  10. 2023Towards the TopMost: A Topic Modeling System Toolkitcited by 21
  11. 2024A Survey on Neural Topic Models: Methods, Applications, and Challengescited by 18
  12. 2022HyperMiner: Topic Taxonomy Mining with Hyperbolic Embeddingcited by 15
38 more
  1. 2022Neural Topic Modeling of Psychotherapy Sessionscited by 13
  2. 2024Topic Modeling as Multi-Objective Contrastive Optimizationcited by 12
  3. 2023Event Temporal Relation Extraction with Bayesian Translational Modelcited by 10
  4. 2022SupervisorBot: NLP-Annotated Real-Time Recommendations of Psychotherapy Treatment Strategies with Deep Reinforcement Learningcited by 8
  5. 2024COMPASS: Computational Mapping of Patient-Therapist Alliance Strategies with Language Modelingcited by 8
  6. 2022Knowledge Management System with NLP-Assisted Annotations: A Brief Survey and Outlookcited by 7
  7. 2023CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modelingcited by 7
  8. 2021Neural Attention-Aware Hierarchical Topic Modelcited by 6
  9. 2023A Topic-aware Summarization Framework with Different Modal Side Informationcited by 6
  10. 2023Diversity-Aware Coherence Loss for Improving Neural Topic Modelscited by 5
  11. 2023Topic-VQ-VAE: Leveraging Latent Codebooks for Flexible Topic-Guided Document Generationcited by 5
  12. 2024Enhancing Short-Text Topic Modeling with LLM-Driven Context Expansion and Prefix-Tuned VAEscited by 5
  13. 2024Self-supervised Topic Taxonomy Discovery in the Box Embedding Spacecited by 4
  14. 2025Bridging the Evaluation Gap: Leveraging Large Language Models for Topic Model Evaluationcited by 4
  15. 2021Evaluation of Thematic Coherence in Microblogscited by 3
  16. 2022A Joint Learning Approach for Semi-supervised Neural Topic Modelingcited by 3
  17. 2023TherapyView: Visualizing Therapy Sessions with Temporal Topic Modeling and AI-Generated Artscited by 3
  18. 2023CUE: An Uncertainty Interpretation Framework for Text Classifiers Built on Pre-Trained Language Modelscited by 3
  19. 2024Comprehensive Evaluation of Large Language Models for Topic Modelingcited by 3
  20. 2025XTRA: Cross-Lingual Topic Modeling with Topic and Representation Alignmentscited by 3
  21. 2025Improving Topic Modeling of Social Media Short Texts with Rephrasing: A Case Study of COVID-19 Related Tweetscited by 3
  22. 2025Sparse Autoencoders are Topic Modelscited by 3
  23. 2021Adversarial Learning of Poisson Factorisation Model for Gauging Brand Sentiment in User Reviewscited by 1
  24. 2022Neural Topic Modeling with Deep Mutual Information Estimationcited by 1
  25. 2022Towards Better Understanding with Uniformity and Explicit Regularization of Embeddings in Embedding-based Neural Topic Modelscited by 1
  26. 2023Graph Contrastive Topic Modelcited by 1
  27. 2023Towards Generalising Neural Topical Representationscited by 1
  28. 2024Enhancing Topic Interpretability for Neural Topic Modeling through Topic-wise Contrastive Learningcited by 1
  29. 2025Merging Embedded Topics with Optimal Transport for Online Topic Modeling on Data Streamscited by 1
  30. 2025S2WTM: Spherical Sliced-Wasserstein Autoencoder for Topic Modelingcited by 1
  31. 2025Toward Purpose-oriented Topic Model Evaluation enabled by Large Language Modelscited by 1
  32. 2026LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language Modelscited by 1
  33. 2022One Configuration to Rule Them All? Towards Hyperparameter Transfer in Topic Models using Multi-Objective Bayesian Optimizationcited by 0
  34. 2022Anchor Prediction: A Topic Modeling Approachcited by 0
  35. 2023Tracking Brand-Associated Polarity-Bearing Topics in User Reviewscited by 0
  36. 2023Cone: Unsupervised Contrastive Opinion Extractioncited by 0
  37. 2023Let the Pretrained Language Models "Imagine" for Short Texts Topic Modelingcited by 0
  38. 2025Understanding Cross-Domain Adaptation in Low-Resource Topic Modelingcited by 0

50 most cited of 53 All 53 (JSON)