+7 (495) 987 43 74 ext. 3304
Join us -              
Рус   |   Eng

Authors

Strizhov V. V.

Degree
Ph. D. (Math.), Associate Professor, Research Fellow, the Chair of Intelligent Systems, Computing Center of the Russian Academy of Sciences
E-mail
strijov@ccas.ru
Location
Moscow
Articles

The construction of hierarchical thematic models for document collection

The paper proposes the use of probabilistic mathematical model. Special attention is paid to the hierarchical mathematical model and, in particular, discuss the properties of algorithms PLSA and LDA. Specific feature of the hierarchical model is to move from the concept of «bag of words» to the «bag of themes» in the implementation of flat clustering algorithms. The algorithm is illustrated with the theses of the Euro-2012 conference and with some synthetic data.
Read more...