A Practical Agent-Based Method to Extract Semantic Information from the Web

Abstract

The semantic Web will bring meaning to the Internet,mak - ing it possible for web agents to understand the information it contains. However,c urrent trends seem to suggest that it is not likely to be adopted in the forthcoming years. In this sense,m eaningful information extraction from the web becomes a handicap for web agents. In this article,w e present a framework for automatic extraction of semantically-meaningful information from the current web. Separating the extraction process from the business logic of an agent enhances modularity,ad aptability,an d maintainability. Our approach is novel in that it combines different technologies to extract information,su rf the web and automatically adapt to some changes.