Ontology Completion with Graph-Based Machine Learning: A Comprehensive Evaluation
Increasing quantities of semantic resources offer a wealth of human knowledge, but their growth also increases the probability of wrong knowledge base entries. The development of approaches that identify potentially spurious parts of a given knowledge base is therefore highly relevant. We propose an...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Machine Learning and Knowledge Extraction |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4990/4/4/56 |
| _version_ | 1797456565930819584 |
|---|---|
| author | Sebastian Mežnar Matej Bevec Nada Lavrač Blaž Škrlj |
| author_facet | Sebastian Mežnar Matej Bevec Nada Lavrač Blaž Škrlj |
| author_sort | Sebastian Mežnar |
| collection | DOAJ |
| description | Increasing quantities of semantic resources offer a wealth of human knowledge, but their growth also increases the probability of wrong knowledge base entries. The development of approaches that identify potentially spurious parts of a given knowledge base is therefore highly relevant. We propose an approach for ontology completion that transforms an ontology into a graph and recommends missing edges using structure-only link analysis methods. By systematically evaluating thirteen methods (some for knowledge graphs) on eight different semantic resources, including Gene Ontology, Food Ontology, Marine Ontology, and similar ontologies, we demonstrate that a structure-only link analysis can offer a scalable and computationally efficient ontology completion approach for a subset of analyzed data sets. To the best of our knowledge, this is currently the most extensive systematic study of the applicability of different types of link analysis methods across semantic resources from different domains. It demonstrates that by considering symbolic node embeddings, explanations of the predictions (links) can be obtained, making this branch of methods potentially more valuable than black-box methods. |
| first_indexed | 2024-03-09T16:09:38Z |
| format | Article |
| id | doaj.art-03722ffab5a24d4582e367c232ffe6b9 |
| institution | Directory Open Access Journal |
| issn | 2504-4990 |
| language | English |
| last_indexed | 2024-03-09T16:09:38Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machine Learning and Knowledge Extraction |
| spelling | doaj.art-03722ffab5a24d4582e367c232ffe6b92023-11-24T16:19:08ZengMDPI AGMachine Learning and Knowledge Extraction2504-49902022-12-01441107112310.3390/make4040056Ontology Completion with Graph-Based Machine Learning: A Comprehensive EvaluationSebastian Mežnar0Matej Bevec1Nada Lavrač2Blaž Škrlj3Jožef Stefan Institute, Jamova 39, 1000 Ljubljana, SloveniaJožef Stefan Institute, Jamova 39, 1000 Ljubljana, SloveniaJožef Stefan Institute, Jamova 39, 1000 Ljubljana, SloveniaJožef Stefan Institute, Jamova 39, 1000 Ljubljana, SloveniaIncreasing quantities of semantic resources offer a wealth of human knowledge, but their growth also increases the probability of wrong knowledge base entries. The development of approaches that identify potentially spurious parts of a given knowledge base is therefore highly relevant. We propose an approach for ontology completion that transforms an ontology into a graph and recommends missing edges using structure-only link analysis methods. By systematically evaluating thirteen methods (some for knowledge graphs) on eight different semantic resources, including Gene Ontology, Food Ontology, Marine Ontology, and similar ontologies, we demonstrate that a structure-only link analysis can offer a scalable and computationally efficient ontology completion approach for a subset of analyzed data sets. To the best of our knowledge, this is currently the most extensive systematic study of the applicability of different types of link analysis methods across semantic resources from different domains. It demonstrates that by considering symbolic node embeddings, explanations of the predictions (links) can be obtained, making this branch of methods potentially more valuable than black-box methods.https://www.mdpi.com/2504-4990/4/4/56machine learningembeddingontology completionlink predictionexplainability |
| spellingShingle | Sebastian Mežnar Matej Bevec Nada Lavrač Blaž Škrlj Ontology Completion with Graph-Based Machine Learning: A Comprehensive Evaluation Machine Learning and Knowledge Extraction machine learning embedding ontology completion link prediction explainability |
| title | Ontology Completion with Graph-Based Machine Learning: A Comprehensive Evaluation |
| title_full | Ontology Completion with Graph-Based Machine Learning: A Comprehensive Evaluation |
| title_fullStr | Ontology Completion with Graph-Based Machine Learning: A Comprehensive Evaluation |
| title_full_unstemmed | Ontology Completion with Graph-Based Machine Learning: A Comprehensive Evaluation |
| title_short | Ontology Completion with Graph-Based Machine Learning: A Comprehensive Evaluation |
| title_sort | ontology completion with graph based machine learning a comprehensive evaluation |
| topic | machine learning embedding ontology completion link prediction explainability |
| url | https://www.mdpi.com/2504-4990/4/4/56 |
| work_keys_str_mv | AT sebastianmeznar ontologycompletionwithgraphbasedmachinelearningacomprehensiveevaluation AT matejbevec ontologycompletionwithgraphbasedmachinelearningacomprehensiveevaluation AT nadalavrac ontologycompletionwithgraphbasedmachinelearningacomprehensiveevaluation AT blazskrlj ontologycompletionwithgraphbasedmachinelearningacomprehensiveevaluation |