News Collection 2006
RIRES: Russian Information Retrieval Evaluation Seminar

 Call for participation 
 General principles 
 Test collections 
 Relevance tables 


News Collection


This collection was provided by Yandex in 2006 and contains news from the following sources:

The news in the collection cover the following time intervals:

  • from 18.11.2003 to 24.11.2003 incl. (8 days): "Shevardnadze's resignation"
  • from 01.12.2003 to 09.12.2003 incl. (8 days): "explosion in Essentuki - parliamentary elections"
  • from 31.03.2004 to 07.04.2004 incl. (8 days): "usual week"

Dataset Parameters
  • Size: 75 Mb
  • Number of documents: ~31 500
  • Encoding: cp1251
Rights to Use

Rights to use this collection are granted by Yandex, the owner of the collection. To get access to the collection you must sign the usage agreement (in Russian).


The collection is distributed in three xml files (data format).

Tracks in Which the Collection Was Used
In ROMIP'2005 in the news clustering track we used another collection.