06月07日(Fri) 09:00〜11:20 C会場(-国際会議場202号室)
| 演題番号 | 4C1-IOS-4b-1 |
|---|---|
| 題目 | Accessing Linked Data with A Simple Integrated Ontology |
| 著者 | Lihua Zhao(National Institute of Informatics) Ichise Ryutaro(National Institute of Informatics) |
| 時間 | 06月07日(Fri) 09:00〜09:20 |
| 概要 | The Web of Data provides abundant knowledge, which contains a huge amount of data sets and links among them. In order to access the linked data, we have to be familiar with the ontology of each data set. However, because of the heterogeneous and big ontologies in the linked data, it is time consuming and difficult to manually observe which ontology schemas are important for describing a specific instance and how the same concept is represented differently in ontologies. In order to help linked data users easily understand the ontologies and access various data sets, we need a global ontology constructed by grouping related ontology classes and properties and by retrieving core ontology schemas. In this paper, we propose a semi-automatic ontology integration framework that reduces the heterogeneity of ontologies using ontology similarity matching on SameAs graph patterns and retrieves frequently used core ontology schemas from the linked data with machine learning methods. This framework constructs a high-quality integrated ontology, which is easily understandable and effective in knowledge acquisition from linked data. |
| 論文 | PDFファイル |