
Training and application ofneural network language model for ontology population.
Author(s) -
Павел Ломов,
Marina Malozemova
Publication year - 2020
Publication title -
trudy kolʹskogo naučnogo centra ran
Language(s) - English
Resource type - Journals
ISSN - 2307-5252
DOI - 10.37614/2307-5252.2020.8.11.003
Subject(s) - ontology , computer science , upper ontology , suggested upper merged ontology , process ontology , ontology based data integration , natural language processing , ontology inference layer , population , artificial intelligence , ontology alignment , implementation , owl s , information retrieval , software engineering , domain knowledge , semantic web , philosophy , demography , epistemology , semantic web stack , sociology
The article considers one of the subtasks of ontology learning -the ontology population, which implies the extension of existing ontology by new instances without changing the ontology structure. A brief overview ofexisting ontology learning approaches and their software implementations is presented. A highly automated technology for ontology population based on training and application of the neural network language model to identify and extract potential instancesof ontology classes from domain texts is proposed. The main stages of its application, as well as the results of its experimental evaluation and the main directions of its further improvement are considered.