Building ontological knowledge links based on searching and analyzing text links

Abstract

The article discusses the main aspects of controlling the referential connectivity of a set of electronic texts on the example of the field of knowledge of biomedicine. The complexity of finding the occurrences of one term in the text of the definition of another term is analyzed. Considered the problem of finding the occurrences of potential text links in the text of the definition of a particular term. The main problems are indicated: the use of terms in various syntactic and grammatical forms (various endings, cases, prepositions), as well as the search for terms whose name consists of several words (search for phrases). Among the priorities are the following: the definition of the basis of the word in the name of the term, the search for occurrences, taking into account phrases. There are options for solving these problems with the help of modern text processing methods: splitting into n-grams, stemming, the use of regular expressions. The author proposes the idea of creating a software tool that allows for the binding of a finite set of documents by the method of building ontological links based on the analysis of the identified text links.