@inproceedings{Craven:1998,
title = {Learning to Extract Symbolic Knowledge from the World Wide Web},
author = {Mark Craven and Dan DiPasquo and Dayne Freitag and Andrew McCallum and Tom Mitchell and Kamal Nigam and Se\'{a}n Slattery},
booktitle = {Proc. AAAI-98},
url = {http://citeseer.nj.nec.com/9546.html},
year = {1998},
abstract = {The World Wide Web is a vast source of information accessible to computers, but understandable only to humans. The goal of the research described here is to automatically create a computer understandable knowledge base whose content mirrors that of the World Wide Web. Such a knowledge base would enable much more effective retrieval of Web information, and promote new uses of the Web to support knowledge-based inference and problem solving. Our approach is to develop a trainable information extraction system that takes two inputs: and ontology defining the classes and relations of interest, and a set of training data consisting of labeled regions of hypertext representing instances of these classes and relations...},
keywords = {web_data_extraction }
}