Audio, videos and slides of this seminar are available in the Multimedia section.

 Pdf: Seminar Program

The amount of digital data produced strongly increased. The web with its social networks, the traces left on electronic commercial websites and its search engines, the data gathered through devices for personal mobile communication and sensor networks are just a few examples of this authentic information flood.

The possibilities to automatically analyze such data could open up unthinkable scenarios for applications by creating a new range of services based on knowledge. Research took up the challenge creating new techniques of information mining to allow for instance automatic classification, the discovery of hidden rules and associations in the data sequence, the recognition of semantic entities in texts and the implicit user profiling.

Dunja Mladenic and Giovanni Semeraro are research leaders in this sector where FUB has a tradition of innovative research. The morning session will focus on debating main techniques for automatic information extraction from text, databases and web including the solution of unpublished and actual problems like the TV program La Ghigliottina.

The afternoon session will be dedicated to applications. There are virtually no productive and service sectors where these technologies cannot be implemented. Just to name a few known cases, they are the base for the foundation of the advanced methods for client relations management, quality control, claims processing, fraud uncovering, and credit supply. New promising applicative sciences based on automatic information retrieval are being created now by computational advertising and Web 2.0 mining.

The various speakers will take into account this multifaceted and stimulating panorama.