Regularization, robustness and sparsity of probabilistic topic models
We propose a generalized probabilistic topic model of text corpora which can incorporate heuristics of Bayesian regularization, sampling, frequent parameters update, and robustness in any combinations. Wellknown models PLSA, LDA, CVB0, SWB, and many others can be considered as special cases of the p...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
Institute of Computer Science
2012-12-01
|
| Series: | Компьютерные исследования и моделирование |
| Subjects: | |
| Online Access: | http://crm.ics.org.ru/uploads/crmissues/crm_2012_4/12403.pdf |
| Summary: | We propose a generalized probabilistic topic model of text corpora which can incorporate heuristics of Bayesian regularization, sampling, frequent parameters update, and robustness in any combinations. Wellknown models PLSA, LDA, CVB0, SWB, and many others can be considered as special cases of the proposed broad family of models. We propose the robust PLSA model and show that it is more sparse and performs better that regularized models like LDA. |
|---|---|
| ISSN: | 2076-7633 2077-6853 |