WebCrow uses four techniques in parallel to find possible answers to a clue. Two involve looking for the clue or a near match in a database of solved crosswords or using a dictionary. Another uses rules known to work on a kind of Italian clue with two letter answers and the fourth technique is to search the internet.Link
WebCrow performs a search using key words extracted from the clue. It can usually find the answer by looking at the small previews that appear with the search engine results, but it can scan whole pages if necessary. Words of the right length that crop up most often in the results are taken to be possible answers...
Tony Veale works on software that can deal with human language at University College Dublin, Ireland, and watched WebCrow in action. He told New Scientist he was impressed. "It's part of a trend to use the web as a shallow source of human knowledge for artificial intelligence," he says.
I write books. My latest is a YA science fiction novel called Homeland (it's the sequel to Little Brother). More books: Rapture of the Nerds (a novel, with Charlie Stross); With a Little Help (short stories); and The Great Big Beautiful Tomorrow (novella and nonfic). I speak all over the place and I tweet and tumble, too.