For the purposes of this chapter, an information agent can be described as a distributed system that receives a goal through its user interface, gathers information relevant to this goal from a variety of sources, processes this content as appropriate, and delivers the results to the users. We focus on the second stage in this generic architecture. We survey a variety of information extraction techniques that enable information agents to automatically gather information from heterogeneous sources.
Mendeley saves you time finding and organizing research
Choose a citation style from the tabs below