TAC 2010 Knowledge Base Population (KBP2010) Track
Overview
Question Answering and Information Extraction have been studied over the past
decade; however evaluation has generally been limited to isolated targets or
small scopes (i.e., single documents). The Knowledge Base Population (KBP) Track
at TAC 2010 will explore extraction of information about entities with reference to an
external knowledge source. Using basic schema for persons, organizations, and
locations, nodes in an ontology must be created and populated using unstructured
information found in text. A collection of
Wikipedia Infoboxes will
serve as a rudimentary initial knowledge representation.
What's New
September 12: System Description paper deadline and instructions are up!
July 1: 55 teams registered for the task so far!
June 14:
Task definition is updated.
Apr 1:
Participant annotation guideline is posted.
Mar 13: KBP participants may be interested in the joint
RTE-KBP pilot task for
validating slots.
Organizing Committee
Hoa Trang Dang (NIST, hoa.dang@nist.gov)
Ralph Grishman (Coordinator, New
York University, grishman@cs.nyu.edu)
Heng Ji (Coordinator, City University
of New York, hengji@cs.qc.cuny.edu)
Paul McNamee (Johns Hopkins
University, paul.mcnamee@jhuapl.edu)
Boyan Onyshkevych (Department of Defense)
Heather Simpson (LDC,
hsimpson@ldc.upenn.edu)
Stephanie M. Strassel (LDC,
strassel@ldc.upenn.edu)
|