Vasiliy Alekseev


2020

pdf bib
TopicNet: Making Additive Regularisation for Topic Modelling Accessible
Victor Bulatov | Vasiliy Alekseev | Konstantin Vorontsov | Darya Polyudova | Eugenia Veselova | Alexey Goncharov | Evgeny Egorov
Proceedings of the Twelfth Language Resources and Evaluation Conference

This paper introduces TopicNet, a new Python module for topic modeling. This package, distributed under the MIT license, focuses on bringing additive regularization topic modelling (ARTM) to non-specialists using a general-purpose high-level language. The module features include powerful model visualization techniques, various training strategies, semi-automated model selection, support for user-defined goal metrics, and a modular approach to topic model training. Source code and documentation are available at https://github.com/machine-intelligence-laboratory/TopicNet