The Internet presents numerous sources of useful information--telephone directories, product catalogs, stock quotes, event listings, etc. Recently, many systems have been built th...
We propose a method for modeling complex Web sources that have active user interaction requirements. Here active" refers to the fact that certain information in these sources ...
We consider the problem of template-independent news extraction. The state-of-the-art news extraction method is based on template-level wrapper induction, which has two serious li...
Junfeng Wang, Xiaofei He, Can Wang, Jian Pei, Jiaj...
In this paper, we describe a method for automatic creation of a knowledge source for text generation using information extraction over the Internet. We present a prototype system ...
The Web has been the star service on the Internet, however the outsized information available and its decentralized nature has originated an intrinsic difficulty to locate, extract...