The paper is dedicated to solving the problem of optimal text classification in the area of automated detection of typology of texts. In conventional approaches to topicality-based text classification (including topic modeling), the number of clusters is to be set up by the scholar, and the optimal number of clusters, as well as the quality of the model that designates proximity of texts to each other, remain unresolved questions. We propose a novel approach to the automated definition of the optimal number of clusters that also incorporates an assessment of word proximity of texts, combined with text encoding model that is based on the system of sentence embeddings. Our approach combines Universal Sentence Encoder (USE) data pre-processing, agglomerative hierarchical clustering by Ward’s method, and the Markov stopping moment for optimal clustering. The preferred number of clusters is determined based on the “e-2” hypothesis. We set up an experiment on two datasets of real-world labeled data: News20 and BBC. The proposed model is tested against more traditional text representation methods, like bag-of-words and word2vec, to show that it provides a much better-resulting quality than the baseline DBSCAN and OPTICS models with different encoding methods. We use three quality metrics to demonstrate that clustering quality does not drop when the number of clusters grows. Thus, we get close to the convergence of text clustering and text classification.

A criterion is proposed that determines the moment when the growth pattern of the monotonic numerical sequence varies from the linear to the parabolic one. The criterion is based on the comparison of squares of errors for the linear and the incomplete quadratic approximation. The approximating functions are constructed locally, only at those points that are located near a possible change in nature of the increase in the sequence.

This article presents the period of development of medicine in Russia from the beginning of the 9th century until the end of the 18th century. Before 1613, most of the population in Russia did not have access to qualified medical care and relied on traditional folk remedies. After conversion of Kievan Rus’ to Byzantium Christianity, monks provided basic medical care in the monasteries along with folk healers. At the same time, the ruling classes had access to qualified medical assistance, which was provided by foreign physicians. During the reign of Mikhail Fyodorovich Romanov (1613–1645) many foreign doctors were invited to Russia, including representatives of the Netherlands, graduates of the Leiden University. The development of medical education in European areas was largely carried out by foreign doctors, in particular,doctors from Holland. Hermann Kaau-Boerhaave and Pavel Zakharievich Condoidi, Dutch representatives and graduates of the Leiden University played a particularly important role in the development of Russian Medicine in the 18th century. In 1654 the first medical school was opened in Russia. State institutions were established to organise and supervise the work of pharmacists, doctors medicinae and barber-surgeons. The treatment of patients in the 17–18th centuries advanced from primitive folk to more advanced methods based on science including surgical interventions.