TopSBM: Topic Models based on Stochastic Block Models
Topic models are a popular way to extract information from text data, but its most popular flavours (based on Dirichlet priors, such as LDA) make unreasonable assumptions about the data which severely limit its applicability. Here we explore an alternative way of doing topic modelling, based on stochastic block models (SBM), thus exploiting a mathematical connection with finding community structure in networks.
TopSBM: Topic Models based on Stochastic Block Models TopSBM: Topic Models based on Stochastic Block Models Check a simple example or try it online in Google Colab or in the ATAP Binder . See also this notebook to go beyond just text data, the topSBM implementation of the Australian Text Analytics Platform (ATAP) for improved visualizations, and the Python package graph-tool and its detailed documentation for more details on the SBM inference . Installation and usage instructions To run it yourself, you need to: Install graph-tool : see detailed installation instructions . or using Docker : do
Explore this link on the map →saved by
related reading
- Topic Modeling in Python: Latent Dirichlet Allocation (LDA) | Towards Data Sciencetowardsdatascience.com
- H-Nets - the Past | Goomba Labgoombalab.github.io
- Google Colabcolab.research.google.com
- Writing - betanalpha.github.iobetanalpha.github.io
- Paper Trailspapertrailshq.com
- Idea Listjzhao.xyz
- Okapi BM25 - Wikipediaen.wikipedia.org
- Bag-of-words model - Wikipediaen.wikipedia.org
- Hierarchical Modelingbetanalpha.github.io
- Notebooksbactra.org
- Language Modelinglena-voita.github.io
- Probabilistic Relevance Frameworkstaff.city.ac.uk