Obtaining knowledge from the Web using fusion and summarization techniques

Nowadays, information and knowledge are fundamental in our society. This has induced an information overload problem in the Internet. For this reason, we propose to create an automatic system to retrieve, select, and extract information from the Web whose methodology is based on fusion techniques. The system, called Diana, facilitates and improves the identification of interesting contents, and it allows to extract the most relevant information about a certain topic from the Web as a summary. To do this, we have developed algorithms that use semantic tools, Natural Language Processing (NLP) techniques, statistics, a generic gazetteer, and fusion methods. The development of the system is undergoing, but the preliminary results that we have obtained so far are very promising and show the interest of our proposal.