KnowItAll, a search engine under development at the University of Washington and partially funded by DARPA and Google, trawls the Web for data and then collates it in the form of a list providing information that probably doesn't exist on any single Web page. The ultimate aim is to have KnowItAll answer questions such as "list all British scientists born before 1900." For any input noun (such as "scientists," "guitarists," etc.) the engine tries to find sentences on Web sites that contain that noun and looks for words that often appear after it. In this way it might find the phrases "scientists such as" and "scientists including," which it then feeds to 12 search engines and extracts the words that tend to follow (which are often scientists' names). KnowItAll then returns a long list of scientists' names, each one accompanied by its percentage probability of being correct, as measured by frequency of occurrence of the names on Web sites. Users will be able to choose the level of confidence they want in the data.
posted by Marcus Zillman |
4:00 AM
