Feature generation for textual information retrieval using world knowledge

Imagine an automatic news filtering system that tracks company news. Given the news item "FDA approves ciprofloxacin for victims of anthrax inhalation", how can the system know that the drug mentioned is an antibiotic produced by Bayer? Or consider an information professional searching for data on RFID technology -- how can a computer understand that the item "Wal-Mart supply chain goes real time" is relevant for the search? Algorithms we present can do just that.