UDC 007:681.512.2
EXTRACTING FACTS FROM POLITICAL ARTICLES BASED ON GENUS-SPECIES UNIFICATION OF CONCEPTS
I. Yu. Kashirin, Dr. in technical sciences, full professor, 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.
This paper examines a new method for extracting factual information from political articles published in
English-language electronic media. The novel approach involves representing complex facts using feature
structures containing not only role-based elements but also hierarchical indices. The indices reflect generic,
causal, and meronymic relationships across a set of vocabulary concepts in the article text. Algebraic operations on feature structures enable the analysis and synthesis of formal descriptions of facts.
The experimental part of the material is based on the use of the Python programming language toolkit
v.3 (Anaconda 3), LLM DistilBERT, the mIYu-bert v.3.7 software package, and the IntellectualParsing.ipynb
v.2.0 pattern matching toolkit. The completed series of experiments allows us to qualify the new method for
unifying feature structures as the basis for a technology that is equal in efficiency to currently available international analogues and surpasses them in computational complexity. The aim of this paper is to describe a new method for extracting factual data from electronic information resources. The method is based on a new algorithm for unifying feature structures.
Key words: unification theory, fact extraction, natural language analysis, hierarchical numbers, universal algebras, DistilBERT language models, artificial intelligence