ROMIP: Russian Information Retrieval Evaluation Seminar

 General principles 
 Test collections 
 Relevance tables 


Format of results for 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="" trackId="ROMIP-2007-Web-classification">
<!-- for legal documents classification trackId="ROMIP-2007-Legal-classification" -->
<!-- for web documents classification trackId="ROMIP-2007-Webpage-classification" -->

<romip:run> <romip:systemID>Yellow</romip:systemID> <romip:runID>MyRunId</romip:runID> </romip:run>
<result> <document name=""> <topic>240</topic> </document> <document name=""> <topic>184</topic> <topic>202</topic> <topic>131</topic> <topic>163</topic> </document> </result> </romip:taskresult>
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.

For web site classifictaion track items (document tag) are sites (in this case identifier is site name). In case of page classification items are documents (document identifier is value of document tag in its description in the documents collection). Identifier should be specified as value of name attribute of document tag.

Identifiers of predicted topics should be stored as set of topic tags. Each topic tag contains identifier of one topic. Topic identifiers should match topics identifiers from the training set.

IMPORTANT: Up to 5 topics per item are allowed.