Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

7

ML
2015
ACM

favoriteEmaildiscussreport

25views Machine Learning» more ML 2015»

Additive regularization of topic models

8 years 12 days ago

Additive regularization of topic models

Download userpages.umbc.edu

Abstract. Probabilistic topic modeling of text collections is a powerful tool for statistical text analysis. Determining the optimal number of topics remains a challenging problem in topic modeling. We propose a simple entropy regularization for topic selection in terms of Additive Regularization of Topic Models (ARTM), a multicriteria approach for combining regularizers. The entropy regularization gradually eliminates insigniﬁcant and linearly dependent topics. This process converges to the correct value on semi-real data. On real text collections it can be combined with sparsing, smoothing and decorrelation regularizers to produce a sequence of models with diﬀerent numbers of well interpretable topics.

Konstantin Vorontsov, Anna Potapenko

Real-time Traffic

Machine Learning | ML 2015 |

claim paper

Related Content

» Regularization Methods for Additive Models

» Topic modeling with network regularization

» Sparse LSSVMs using additive regularization with a penalized validation criterion

» Learning evolving and emerging topics in social media a dynamic nmf approach with temporal...

» Semisupervised topic modeling for image annotation

» Combining Speech Retrieval Results with Generalized Additive Models

» Supervised Topic Models

» Parsimonious additive models

» A Comparative Study of Utilizing Topic Models for Information Retrieval

» MinimaxOptimal Rates For Sparse Additive Models Over Kernel Classes Via Convex Programming

Post Info
More Details (n/a)

Added	14 Apr 2016
Updated	14 Apr 2016
Type	Journal
Year	2015
Where	ML
Authors	Konstantin Vorontsov, Anna Potapenko

Comments (0)