====================================================================
Call for Participation ROMIP'2009
The Seventh Russian Information Retrieval Evaluation Seminar
March 2009 - September 2009
http://www.romip.ru/en
--------------------------------------------------------------------
Registration is now open for ROMIP'2009, the leading Russian text and image
information retrieval initiative.
---------------------------------------------------------------------
The Russian Information Retrieval Evaluation Seminar (ROMIP) is an annual
retrieval system evaluation campaign that, in many respects, is similar to
other world information retrieval forums such as TREC, CLEF, NTCIR.
The distinctive features of ROMIP are:
* Focus on the problems of information retrieval in Russian language
* Unique large scale Russian language collections
* Tracks that are not available in other related initiatives
The seminar is a perfect opportunity to check your information retrieval and
natural language processing approaches and algorithms using industry
standard evaluation methodologies. The leading Russian IR researchers and
companies traditionally participate in the seminar and you will be able to
objectively compare your results with theirs.
In addition to text retrieval ROMIP also includes several image retrieval
tracks.
The final workshop will be held in conjunction with RCDL'2009
(http://rcdl.ru) and will be held in September, 2009, in Petrazavodsk,
Russia.
Official languages: Russian and English
Tracks
------
* Ad hoc text retrieval
- in a collection of Web pages
- in a collection of legal documents
- in a mixed collection
* Text classification
- of legal documents
- of Web sites
- of Web pages
* News clustering
* Query-biased summarization
* Search by sample document or text fragment
* Fact extraction from news
* Image tracks
- Content based image retrieval
- Near duplicate detection
A detailed track description is available on the the ROMIP website
(http://romip.ru).
ROMIP Test Collections
----------------------
* Web collection Narod.Ru (700.000 documents)
* Web collection KM.Ru 2007 (3.000.000 documents)
* Web collection By.web 2007 (1.500.000 documents)
* Web collection DMOZ (300.000 documents)
* Collection of Legal documents 2007 (300.000 documents)
* News collection (31.500 documents from 25 news agencies)
* Image collection (20.000 images, Flickr based)
* Collection of fuzzy image duplicates (37.800 images)
The text collections are in Russian language. The image collections are
language independent. The query sets for the retrieval tasks are from logs
of popular search engines.
For further details about the collections please see the ROMIP web site.
(http://romip.ru)
Important dates
---------------
Requests for participation: March 8, 2009 Collection and task delivery:
April 1, 2009 Submission of results: up to May 20, 2009 Result of
evaluation: July 15, 2009 Paper submission: August 15, 2009
Workshop: September 16, 2008
How to participate
------------------
Please, submit your application to [log in to unmask] and provide the following
information:
* List of tracks you are interested in
* Contacts (organization, email of contact person)
* Name and brief description of the system/team
to be published on the ROMIP website
Organizing committee
--------------------
Mikhail Ageev (Moscow State University, Russia)
Alexander Antonov (Galaktika-Zoom, Moscow, Russia)
Pavel Braslavski (Yandex, Ekaterinburg, Russia)
Maxim Gubin (Symantec Inc., USA)
Boris Dobrov (UIS RUSSIA, Moscow, Russia)
Mikhail Kostin (Mail.Ru, Moscow, Russia)
Igor Kuralenok (St Petersburg State University, Russia)
Igor Nekrestyanov (St Petersburg State University, Russia)
Marina Nekrestyanova (Nebuad, St. Petersburg, Russia)
Vladimir Pleshko (RCO, Moscow, Russia)
Ilya Segalovich (Yandex, Moscow, Russia)
Vlad Shabanov (Vertical Search, Moscow, Russia)
Natalia Vassilieva (HP Labs, Russia)
Further details
---------------
Web site: http://romip.ru
Please send your questions to the ROMIP forum
(http://www.yahoogroups.com/group/romip) or directly to organizers
([log in to unmask]).
|