Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Confidence Estimation Methods for Partially Supervised Relation Extraction
 

Summary: Confidence Estimation Methods
for Partially Supervised Relation Extraction
Eugene Agichtein
Abstract
Text documents convey valuable information about entities
and relations between entities that can be exploited in struc-
tured form for data mining, retrieval, and integration. A
promising direction is a family of partially-supervised re-
lation extraction systems that require little manual training.
However, the output of such systems tend to be noisy, and
hence it is crucial to be able to estimate the quality of the ex-
tracted information. We present Expectation-Maximization
algorithms for automatically evaluating the quality of the ex-
traction patterns and derived relation tuples. We demonstrate
the effectiveness of our method on a variety of relations.
1 Overview
Text documents convey valuable structured information. For
example, medical literature contains information about new
treatments for diseases. More specifically, information ex-
traction systems can identify particular types of entities (such

  

Source: Agichtein, Eugene - Department of Mathematics and Computer Science, Emory University

 

Collections: Computer Technologies and Information Sciences