Conf: CLEF 2006

Thierry Hamon thierry.hamon at LIPN.UNIV-PARIS13.FR
Fri Mar 17 16:47:19 UTC 2006

Date: Fri, 17 Mar 2006 17:07:29 +0100
From: Christelle Ayache <ayache at>
Message-Id: < at>



The CLEF series of system evaluation campaigns aims at promoting
research into the design and development of user-friendly,
multilingual, multimodal retrieval systems.

Registration for CLEF 2006 is now open.

The objective of CLEF 2006 is to test different aspects of mono- and
cross-language information retrieval system performance. There are
eight tracks this year:

1. Multilingual Document Retrieval on News Collections (Ad-Hoc)
2. Mono- and Cross-Language Information Retrieval on Structured Scientific 
Data (Domain-Specific)
3. Interactive Cross-Language Information Retrieval (iCLEF)
4. Multiple Language Question Answering (QA at CLEF)
5. Cross-language Retrieval in Image Collections (ImageCLEF)
6. Cross-Language Spoken Document Retrieval (CL-SR)
7. Multilingual Web Track (WebCLEF)
8. Cross-Language Geographical Retrieval (GeoCLEF)


Data Release - from 15 February 2006
Topic Release - from 1 April 2006
Submission of Runs by Participants - from 15 May 2006
Release of relevance assessments and individual results - from 15 July 2006
Submission of paper for Working Notes - 15 August 2006 Workshop - 20-22 
September (in conjunction with ECDL 2006)


The CLEF 2006 multilingual corpora include:

- news documents in 12 European languages
- social science databases in German and Russian
- photographic and medical image collections with text and/or annotations 
in several languages
- spontaneous conversational speech in English and Czech
- multilingual collection of web documents from European governmental sites

For full details on the CLEF Agenda and Task Description for 2006 and 
instructions on How to Participate, see

For further information, contact:
Carol Peters - ISTI-CNR
Tel: +39 050 315 2987
Fax: +39 050 315 2810
E-mail: carol.peters at

Message diffusé par la liste Langage Naturel <LN at>
Informations, abonnement :
English version          : 
Archives                 :

La liste LN est parrainée par l'ATALA (Association pour le Traitement
Automatique des Langues)
Information et adhésion  :

More information about the Ln mailing list