Topic Modelling Meets Deep Neural Networks: A Survey
arXiv:2103.00498
Abstract
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.
arXiv commentA review on Neural Topic Models
References in corpus (11)
- Auto-Encoding Variational Bayes
- Discovering Discrete Latent Topics with Neural Variational Inference
- WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling
- Stick-Breaking Variational Autoencoders
- Reparameterization Gradients through Acceptance-Rejection Sampling Algorithms
- Recurrent Hierarchical Topic-Guided RNN for Language Generation
- Discriminative Topic Modeling with Logistic LDA
- Coherence-Aware Neural Topic Modeling
- Neural Topic Modeling with Bidirectional Adversarial Training
- Neural Topic Model via Optimal Transport
- Neural Topic Modeling with Cycle-Consistent Adversarial Training