The European Union-funded Sealife project has developed a Web browser capable of understanding the technical terms used in life sciences and automatically finding additional resources and services related to those terms. The life sciences community has developed numerous databases for storing information, which are now available to researchers through grid services. However, connecting those grid services to other scientific information available on the Web has been problematic. The Sealife project has developed a semantic grid browser designed to seamlessly integrate the Web with grid services to make the grid services more accessible. "It tries to understand what it finds on Web pages, interprets this content, and then links it, on the fly, to services that might be useful to the user," says Sealife project coordinator Michael Schroeder.
The key to the Sealife browser is a semantic hyperlink in the browser used to direct users to relevant services. The Sealife browser must first understand the content of the page and identify terms that could be linked to grid services. Sealife uses algorithms to determine the context of a word based on other words on the page.
In an international competition to identify the names of genes, the Sealife algorithm won with an 81 percent success rate. Schroeder says the success rate is now 87 percent. The browser also must be able to comprehend the ontology in order to understand identified terms. "We developed algorithms that grind through this data, identify the key concepts, and then the ontology editor offers these concepts to you," Schroeder says. "If you agree, it then searches the Web to find things that look like definitions."
From ICT Results
View Full Article
Abstracts Copyright © 2009 Information Inc., Bethesda, Maryland, USA
No entries found