Диссертации, представленные на защиту и подготовленные в НИУ ВШЭ

Nowadays, ontologies are widely used to improve the convenience of information organisation and access to it in fields such as artificial intelligence, software engineering, biomedical informatics, healthcare, enterprise bookmarking, industrial projects, etc. We focus on Ontology-Based Data Access (OBDA) with expressive ontologies, where an ontology is used as a helpful tool for supporting query answering for distributed and heterogeneous data sources. Answering various types of queries mediated by a description logic ontology has been known as an essential reasoning problem in knowledge representation since the early 1990s. We explore the practical potential of specific expressive ontology with a covering axiom in ontology-mediated query (OMQ) answering tasks and focus on challenges associated with chosen ontology type. This study allows us to provide theoretical boundaries of covering axiom usage for OBDA and constructive rewriting of OMQs answering into datalog programs. Additionally, we compare two different approaches to identify the profitability of logic reasoning via OMQ rewriting and graph neural network data labelling followed by querying obtained full-labelled graph.