Thesaurus-Based Topic Models and Their Evaluation
Natalia Loukachevitch, Kirill Ivanov, Boris V. Dobrov · 2018
In this paper we study thesaurus-based topic models and evaluate them from the point of view of topic coherence. Thesaurus-based topic model enhances scores of related terms found in the same text, which means that the model encourages these terms to be in the same topics. We evaluate various variants of such models. At the first step, we carry out manual evaluation of the obtained topics. At the second step, we study the possibility to use the collected manual data for evaluating new variants of thesaurus-based models, propose a method and select the best of its parameters in cross-validation. At the third step, we apply the created evaluation method to estimate the influence of word frequencies on adding thesaurus relations during generating topic models.