Q: Is wrapper induction practical?

• Tested on several domains OKRA email address locator BigBook yellow-pages AltaVista search engine Corel stock photography catalog

• Measured # pages needed for 100% accuracy on test suiteas function of recognizer error rates

• Overall performance 0.2 CPU sec/attribute/KB ? total ? 1 CPU minute  4–44 pages needed for 100% accuracy

Previous slide

Next slide

Back to first slide

View graphic version