Method for Linking Named Entities to Wikidata Concepts for Russian Texts

The paper presents a method for automatically linking named entities in Russian texts with concepts from the Wikidata knowledge base. The method is based on the use of existing tools for searching named entities and semantic analysis of the correspondence of a given entity to a concept in the knowledge base. The method can be used to generate a linked corpus of texts. Unlike existing methods, it is not based on machine learning, but on the analysis of both the named entity itself and its attributes and associated words. Experiments showed an increase in the accuracy of entity matching for new texts.