|  |
Format of training set for classification tracks
Training set is an XML file with the following structure:
<?xml version="1.0" encoding="windows-1251" ?>
<topic-set xmlns:romip="http://www.romip.ru/data/classification" collectionId="ROMIP-2004-DMOZ" id="dmoz-training-2007">
<!-- for legal documents classification collectionId="ROMIP-Legal2007" id="legal-training-2007" -->
<romip:header xmlns:romip="http://www.romip.ru/data/common">
<romip:version>1.1</romip:version>
<romip:license type="public" uri="http://romip.ru/license/public.html" />
<romip:description> This file contains definition of taxonomy and training set for...</romip:description>
</romip:header>
<topic id="202" name="Business->Armament_and_Defense">
<document>www.uralarms.ru</document>
<document>www.sokolplant.ru</document>
</topic>
<topic id="240" name="Sport->Frisbee">
<document>www.frisbee.ru</document>
</topic>
...
</topic-set>
|
