USC/ISI Automatic Data Extraction Demo

Step 4: Extracting AUTHOR from test pages using data prototype

Using the patterns of the data prototype learned from the training examples (Step 1), we identify possible extracts on the new (test) pages. Some patterns are specific and identify only the correct examples of the data field; however, other patterns are general and identify many extraneous examples. The test pages in this example came from the same source (amazon.com). However, because the layout of the source has changed, the wrapper was not extracting the data from the new pages.

View data prototype for AUTHOR
View an old page (training examples)
View a new page (test examples)

Next: Cluster extracts
or View final results

**Author names identified by the data prototype on test pages**
**(partial list of 1950 extracts from 20 pages)**
Page 1 Book World Michael Dirda Harry Potter Best Series have Ever Read Ever Read Johanna Solomon Jules Verne of Harry Potter by Harry Potter Louis Sachar Diane Duane Tom Wolfe Carson Levine Julie Edwards Short Stories Juvenile Fiction Science Fiction Humorous Stories Arthur A . Levine	Page 2 A Scott Berg Scott Berg the Very Best Best Ever by Charles Lindbergh Charles Lindbergh Scott Berg Scott Scott Berg Scott Aeronautical Engineering John D . Rockefeller Charles A . Lindbergh Charles A . Lindbergh captures A . Scott Geoffrey C . Ward Michael J . Ybarra on NPR . This during WWII . However found A . Scott by A . Scott Charles A . Lindbergh	Page 3 Materials Fundamentals of Molecular Beam of Molecular Beam Epitaxy Molecular Beam Molecular Beam Epitaxy Beam Beam Epitaxy Materials Fundamentals of Molecular Beam of Molecular Beam Epitaxy Molecular Beam Molecular Beam Epitaxy Beam Beam Epitaxy On Order Academic Pr Book Book News copyright Book News Book News Jeffrey Y . Tsao Jeffrey Y . Tsao
Page 4 Dangerous Idea At Home The Origin Michael Behe s Black Box Black Box Though Kauffman At Home The Selfish The Selfish Gene Selfish Selfish Gene with Richard Brodie Richard Brodie by Stuart Kauffman Stuart Kauffman as Stuart Kauffman Stuart Kauffman Peter Coveney John H . Holland John H . Holland	Page 5 Vladimir Naumovich Vladimir Naumovich Vapnik Naumovich Naumovich Vapnik Janet Kolodner Computer Programming Artificial Intelligence Tom M . Mitchell Thomas M . Mitchell Tom M . Mitchell Thomas M . Mitchell Richard S . Sutton Andrew G . Barto Vladimir S . Cherkassky Filip M . Mulier Christopher D . Manning John W . Sheppard Tom M . Mitchell Richard S . Sutton Christopher D . Manning Ian H . Witten	Page 6 York City Call It Call It Sleep It It Sleep of Henry Roth Henry Roth in James Joyce James Joyce a Rude Stream Rude Stream Blah Blah Perhaps The Unknown Binding by Henry Roth Henry Roth Saul Bellow Cynthia Ozick Abraham Cahan Mary Antin
Page 7 Sierra Nevadas the Great Central the Great Central Valley Great Central Great Central Valley Central Central Valley from San Ramon San Ramon the New Yorker New Yorker Nevada Range the Coastal Range Coastal Range of North America North America Assembling California Bill Bradley Alan Ryan Regional Geology Earth Sciences Galen A . Rowell	Page 8 John Holland and Artificial Systems Artificial Systems Book Description Brian Arthur Brian Mitchel Resnick Computer Bks General Information Artificial Intelligence John H . Holland John H . Holland John H . Holland David E . Goldberg John H . Holland John H . Holland Robert M . Axelrod Christopher G . Langton Stuart A . Kauffman	Page 9 Greatest Generation Look Through like The Greatest like The Greatest Generation The Greatest The Greatest Generation Greatest Greatest Generation the Adirondack Mountains Adirondack Mountains Like Being Beth York My Uncles My Grandfather Every American of Tom Brokaw Tom Brokaw by Tom Brokaw Tom Brokaw John Grisham Bob Woodward Sherry Sontag World War

Next: Cluster extracts
or View final results