Format of results for page classification tracks
Results should be returned as one or several XML files. Each XML file
contains answers for one or several tasks.
XML must have the following structure:
<?xml version="1.0"?>
<romip:taskresult xmlns:romip="http://www.romip.ru/data/classification" trackId="ROMIP-%YEAR%-Webpage-classification">
<!-- for legal documents classification trackId="ROMIP-%YEAR%-Legal-classification" -->
<romip:run>
<romip:systemID>Yellow</romip:systemID>
<romip:runID>MyRunId</romip:runID>
</romip:run>
<result>
<doclist topicID="240">
<docID>1524673</docID>
<docID>340876</docID>
</doclist>
<doclist topicID="184">
<docID>1328572</docID>
<docID>290443</docID>
<docID>1885078</docID>
</doclist>
</result>
</romip:taskresult>
Please use the year of current ROMIP cycle instead of %YEAR% (for example,
2010 for ROMIP'2010).
Tag run is descriprion of the system produced the result.
-
systemID - system identifier provided by ROMIP organizing
commitee.
-
runID - run identifier to distinguish between different runs of
same participant. Value is up to participant.
Tag result describes into which topics item was classified.
Order of docID tags in the doclist is the order of estimated relevance of
documents to the topic.
Document identifier (docID) is value of document tag in it's description
in the documents collection. Topic identifiers (value of topicID
attribute) should match topics identifiers from the training set.
IMPORTANT: if the collection has docURL tags then the docURL values should
be used as the value of docID tags in the results.
|