Summary of Ontology Embedding: a Survey Of Methods, Applications and Resources, by Jiaoyan Chen and Olga Mashkova and Fernando Zhapa-camacho and Robert Hoehndorf and Yuan He and Ian Horrocks
Ontology Embedding: A Survey of Methods, Applications and Resources
by Jiaoyan Chen, Olga Mashkova, Fernando Zhapa-Camacho, Robert Hoehndorf, Yuan He, Ian Horrocks
First submitted to arxiv on: 16 Jun 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper surveys the field of ontology embedding, which represents knowledge from ontologies as vector representations for use with statistical analysis and machine learning. The authors provide a comprehensive overview of the field, categorizing and analyzing over 80 papers that aim to embed different types of ontologies using various technical solutions. The survey covers the semantics of ontologies, the property of faithfulness in ontology embedding, and its applications in ontology engineering, machine learning augmentation, and life sciences. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Ontology embedding is a way to represent knowledge from specialized databases called ontologies as numbers that computers can understand. This helps machines learn and make predictions about things like medical conditions or financial data. Many scientists have written papers on this topic, but there hasn’t been a clear overview of the field until now. The authors of this paper reviewed over 80 of these papers to see what they were saying and how they approached the problem. They found that different researchers used different methods to embed ontologies, and they applied these methods to different types of data. The paper also discusses some challenges and future directions for ontology embedding. |
Keywords
* Artificial intelligence * Embedding * Machine learning * Semantics
