| | |
Summary: Question Answering over Implicitly Structured Web Content
Eugene Agichtein
Emory University
eugene@mathcs.emory.edu
Chris Burges
Microsoft Research
cburges@microsoft.com
Eric Brill
Microsoft Research
brill@microsoft.com
Abstract
Implicitly structured content on the Web such as HTML ta-
bles and lists can be extremely valuable for web search,
question answering, and information retrieval, as the im-
plicit structure in a page often reflects the underlying se-
mantics of the data. Unfortunately, exploiting this infor-
mation presents significant challenges due to the immense
amount of implicitly structured content on the web, lack
of schema information, and unknown source quality. We
present TQA, a web-scale system for automatic question
|
