Summary of Embedding Ontologies Via Incorporating Extensional and Intensional Knowledge, by Keyu Wang et al.
Embedding Ontologies via Incorporating Extensional and Intensional Knowledge
by Keyu Wang, Guilin Qi, Jiaoyan Chen, Yi Huang, Tianxing Wu
First submitted to arxiv on: 20 Jan 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL)
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 In this paper, researchers propose a novel approach to embedding ontologies, called EIKE, which captures both extensional and intensional knowledge within a domain. The authors argue that existing methods fail to consider these two types of knowledge simultaneously. To address this limitation, they develop a unified framework that represents an ontology in two spaces: the extensional space and the intensional space. They apply geometry-based methods to model extensional knowledge and pretrained language models to capture intensional knowledge. The authors demonstrate the effectiveness of EIKE by evaluating it on three datasets for both triple classification and link prediction, outperforming state-of-the-art methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Ontologists have been working with ontologies that contain rich knowledge about a specific domain. These ontologies can be divided into two kinds: extensional and intensional knowledge. Extensional knowledge tells us about the individual things that belong to certain concepts in the ontology, while intensional knowledge explains the properties, characteristics, and relationships between these concepts. Researchers have been trying to embed these ontologies into a way we can understand them better. But so far, they haven’t been able to consider both types of knowledge at the same time. This new approach, called EIKE, is trying to solve this problem. It creates two spaces, one for extensional knowledge and another for intensional knowledge, and uses special methods to capture each type. The authors show that EIKE works better than other approaches by testing it on several datasets. |
Keywords
» Artificial intelligence » Classification » Embedding
