Multilingual Food and Health Ontology Learning Using Semi-Structured and Structured Web Data Sources

  • Authors:
  • Saeed Albukhitan;Tarek Helmy

  • Affiliations:
  • -;-

  • Venue:
  • WI-IAT '12 Proceedings of the The 2012 IEEE/WIC/ACM International Joint Conferences on Web Intelligence and Intelligent Agent Technology - Volume 03
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

The availability of open Web-based information sources such as Wikipedia in semi-structured format made it possible to build or extend multilingual domain ontologies. This work is a part of a project where we are developing a framework for semantic manipulation of health and nutrition information. In this paper, we present ongoing work aiming to build such ontology utilizing Wikipedia and other multilingual online resources automatically. The constructed ontology consists of monolingual ontologies and language-agnostic ontology connecting them. The constructed ontology is built to capture the culture-relevant aspects for each language based on the available concepts for each language. The ontology then could be used in many applications such as cross-lingual information access and multilingual information extraction for the domains of Food and Health. An initial evaluation shows the effectiveness and correctness of the constructed ontology.