Abstract
The paper presents a method for automatically linking named entities in Russian-language texts with concepts from the Wikidata knowledge base. It is based on the use of named entity search tools with subsequent semantic analysis of the correspondence of the found entity to the concept in the knowledge base. The resulting links can later be used to form a linked corpus of texts in any subject area. The difference between the presented method and existing ones is the analysis of both the named entity itself, its attributes, as well as associated words without the use of machine learning methods. This approach allows to increase the accuracy of searching for a corresponding concept in the knowledge base and eliminates the need to constantly retrain the neural network model to recognize new entities added to the knowledge base.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Transactions of the Kоla Science Centre of RAS. Series: Engineering Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
