OLE - A New Ontology Learning Platform
| Authors | |
|---|---|
| Year of publication | 2005 |
| Type | Article in Proceedings |
| Conference | International Workshop on Text Mining Research, Practice and Opportunities - Proceedings |
| MU Faculty or unit | |
| Citation | |
| Web | http://nlp.fi.muni.cz/projects/ole/pubs.html |
| Field | Informatics |
| Keywords | ontology; natural language processing; text mining; knowledge extraction; uncertainty representation |
| Description | Ontologies are commonly considered as one of the essential parts of the Semantic Web, providing a theoretical basis and implementation framework for conceptual integration and information sharing among various domains. In this paper, the main principles and current highlights of the OLE project development are presented and discussed. OLE stands for Ontology LEarning. The purpose of the project is to develop a system for bottom-up automatic generation and merging of domain specific ontologies, representing particular domains of human scientific knowledge. In order to gain ontology concepts from textual resources, various methods can be used. Presently, the method of automatic acquisition of semantic relations is examined. The method and its implementation details are described here, provided with brief comparative overview of other methods used for the development of domain specific ontologies. When merging automatically created ontologies, a need of uncertain information representation arises. The main ideas of representing uncertainty in ontologies and related remarks for future work on the OLE project are mentioned in this paper as well. |
| Related projects: |