caa a22 4500 605477949 CHVBK 20210128100403.0 cr unu---uuuuu 210128e20151001xx s 000 0 eng 10.1007/s10994-014-5476-6 doi (NATIONALLICENCE)springer-10.1007/s10994-014-5476-6 Additive regularization of topic models [Elektronische Daten] [Konstantin Vorontsov, Anna Potapenko] Probabilistic topic modeling of text collections has been recently developed mainly within the framework of graphical models and Bayesian inference. In this paper we introduce an alternative semi-probabilistic approach, which we call additive regularization of topic models (ARTM). Instead of building a purely probabilistic generative model of text we regularize an ill-posed problem of stochastic matrix factorization by maximizing a weighted sum of the log-likelihood and additional criteria. This approach enables us to combine probabilistic assumptions with linguistic and problem-specific requirements in a single multi-objective topic model. In the theoretical part of the work we derive the regularized EM-algorithm and provide a pool of regularizers, which can be applied together in any combination. We show that many models previously developed within Bayesian framework can be inferred easier within ARTM and in some cases generalized. In the experimental part we show that a combination of sparsing, smoothing, and decorrelation improves several quality measures at once with almost no loss of the likelihood. The Author(s), 2014 Probabilistic topic modeling nationallicence Regularization of ill-posed problems nationallicence Probabilistic latent sematic analysis nationallicence Latent Dirichlet allocation nationallicence EM-algorithm nationallicence Vorontsov Konstantin Department of Intelligent Systems at Dorodnicyn Computing Centre of RAS, Institute of Physics and Technology, Moscow, Russia aut Potapenko Anna Computer Science Department, The Higher School of Economics, Moscow, Russia aut Machine Learning Springer US; http://www.springer-ny.com 101/1-3(2015-10-01), 303-323 0885-6125 101:1-3<303 2015 101 10994 https://doi.org/10.1007/s10994-014-5476-6 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s10994-014-5476-6 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Vorontsov Konstantin Department of Intelligent Systems at Dorodnicyn Computing Centre of RAS, Institute of Physics and Technology, Moscow, Russia aut NATIONALLICENCE 700 1- Potapenko Anna Computer Science Department, The Higher School of Economics, Moscow, Russia aut NATIONALLICENCE 773 0- Machine Learning Springer US; http://www.springer-ny.com 101/1-3(2015-10-01), 303-323 0885-6125 101:1-3<303 2015 101 10994