UDC 007.681.512.2
BINARY HIERARCHICAL NUMBERS TO CALCULATE SEMANTIC PROXIMITY OF NATURAL LANGUAGE SENTENCES
I. Yu. Kashirin, Dr. in technical sciences, full professor, department of computational and applied mathematics, RSREU, Ryazan, Russia; orcid.org/0000-0003-1694-7410, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
The article discusses a new technology for calculating semantic proximity of natural language sentences preprocessed by trained neural networks. For software implementation of semantic analysis, Spacy and WordNet tools are used. Automatic verification of political news materials was chosen as subject area. The theory of binary hierarchical numbers is used to calculate numerical parameters of semantic proximity. Basic operations with hierarchical numbers are given. The principle of minimizing the taxonomy complex semantic relations is considered. Hierarchical numbers are used when analyzing generic taxonomy of subject area of natural language sentence. The experimental part of the research was carried out for test software implemented in Python v.3 (Anaconda 3). Source texts of news articles made use of the materials from international publications such as WSJ, PBS News Hour, AC News and others. The performed series of experiments makes it possible to evaluate the technology in question as a technology for calculating semantic proximity of sentences, which is not inferior in efficiency to existing modern international analogues. The aim of the work is to create a new technology used in automated calculation of semantic proximity of natural language constructions for the formation of thematic collections of electronic news materials.
Key words: : binary hierarchical numbers, semantic proximity, generic taxonomy, intelligent data processing, knowledge base, semantic networks, natural language analysis, neural networks.