Clarification re: I.2

To: cse494-f11@rakaposhi.eas.asu.edu
Subject: Clarification re: I.2
From: Subbarao Kambhampati <rao@asu.edu>
Date: Sun, 11 Dec 2011 16:54:25 -0700
Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:sender:date:x-google-sender-auth:message-id:subject :from:to:content-type; bh=MW703dGcoXsxYvGSCnuwuzWFPDRrtuvp0r2fRrJZyXE=; b=P+5i/C9gFQt8RXKU4cMIRa5ZYEZEGv8Ge5eLxpWudXfqEjaoGMak4jahFqmGUYApjL qC6xFY4OBE2YKfX+moYSf4P/Yk4DHo5lmAYLvwB0V9y/PFnBulV0mIuIS9ReVdLcabhi N+2IRscwnmHfXpoidqXlL/WfbPPZRLC1o+9Do=
Sender: subbarao2z2@gmail.com

More than one person seems to have been confused by the word "learning" in I.2 below.

What I am asking is whether the information extracted by most IE (information extraction) methods are meant to be stored in RDF or OWL format.

Semantic web has RDF and OWL standards for specifying structure. Information

extraction aims to extract structure rather than wait for it being manually specified. Are

current day IE approaches aimed at learning what is normally specified in RDF or in

OWL? Why?