Agent-Based Services for the Semantic Web


Thursday, May 6, 2004, 13:00pm

346 ITE

In the semantic web vision, data and information on the Web are defined and linked so that they are both human readable and machine understandable. Machine understandability means that the data have been explicitly prepared for programs and software agents to reason about and reuse. However, most software agents have not been designed to run in a web environment: the agents and web components are working in different models. For example, most software agent frameworks and tools do not support reasoning over content expressed in a mixture of several ontologies. Web components, on the other hand, lack notions of autonomy and a rich message-oriented communication. This thesis suggests adding to a semantic web site a dedicated service agent, capable of understanding the ontologies used by the site and answering queries about the content found on the site. Semantic web tasks are accomplished by the cooperation of personal agents, service agents, and semantic web servers. The semantic web language OWL is used as the agent content language for message passing and interaction. The F-OWL inference engine has been developed to manage logical sentences explicitly stated in the web documents as well as those that can be inferred. Within this thesis a Trading Agent System (TAGA) running in the open Agentcities platform, is used to support the hypothesis and demonstrate how the software agent and semantic web paradigms can be integrated.

We see two main contributions in our work. First, this thesis explores the agent's roles in the service-based semantic web and analyzes how agents and semantic web components can be profitably integrated. Secondly, TAGA provides a flexible and rich environment for simulating agent-based trading in dynamic markets. The enhanced semantic web vision we present is that both human and agents can directly access semantically marked web pages through web interface; an agent can access other agents by exchanging messages in an appropriate agent communication language; personal agents and service agents work together to understand the semantic web content, automate web services and better serve humans.

Committee Members:

  • Dr. Tim Finin (Chairperson)
  • Dr. Marie desJardins
  • Dr. James Hendler
  • Dr. Anupam Joshi
  • Dr. Charles Nicholas
  • Dr. Yun Peng
Academic Advisor: Dr. Tim Finin

OWL Tweet

UMBC ebiquity