CLEF 2006 | How to Participate

How to Participate

In order to participate in CLEF 2006 and have access to the test collections, a registration form and the relevant data release forms must be first compiled, signed, and sent to Carol Peters at the address below (except for the web collection - see following). On receipt of the forms, you will be sent information on how to download the data. For copyright reasons, we have 3 separate sets of data release forms: one for the US newspaper data, one for the EuroGOV web collection, and one for all other document collections (text, image and speech). The EuroGOV forms are downloadable from the WebCLEF  website (see under the EuroGOV link) and should be compiled and sent to the WebCLEF coordinators at the University of Amsterdam. The others are accessible here below.

Some information is repeated on the different forms. The reason for this is that they will be kept on different sites. All forms must be signed by a person authorised by your organisation for such signatures (e.g. Department or Administrative Head or similar).
Please note that previous CLEF participants must resubmit End-User Agreements each year in order to renew their authorisation to access the data covered by this agreement.

Please compile the forms carefully, inserting all relevant information. Read the task descriptions in the Agenda for CLEF 2006 to see which data collections you should request - this depends on the tasks you will be performing. Remember that access to the data will only be provided when we have received signed, original copies of the forms (not electronic or fax versions).

Registration Form

The Registration Form is your statement of intention to participate in CLEF 2006. All participating groups must submit this form. Please fill it in carefully, providing full details of the tasks in which you intend to participate and the languages you will be using. The following table is meant as a guide to help you in identifying which target collections you will need. If you are unsure, please contact either Carol Peters ( or the coordinators of the particular track(s) in which you are interested. Registration remains open until 1 May 2006.



  News:   BG

  News:  DE

News:EN (US/British)

 News: ES

 News: FI

 News: FR

News: IT

News: HU

 News:  NL

 News: PT

News: RU

News: SW

Dom-Spec GIRT-4

Dom-Spec RSSC





 LTU      (to be confirmed)

Speech Corpus

Euro GOV



Frankfurt.R, Der Spiegel & DE SDA (94/95) 

LA Times, Glasgow Herald (94/95) 

 EFE (94/95) 


Le Monde 94 only; FR SDA 94/95

La Stampa 94;     IT SDA 94/95


NRC Handelsblad, Algemeen Dagblad (94/95)













AD-HOC BILINGUAL (choice of collection depends on task)

Sega;Standart (2002)


LA Times, Glasgow Herald (94/95) 



LeMonde 94/95;   FR SDA 94/95


Magyar Hirlap (2002)


P˙blico 94/95; Folha94/95












AD-HOC MONOLINGUAL (collection depends on task)

Sega;Standart (2002) 





LeMonde 94/95;   FR SDA 94/95


Magyar Hirlap (2002)


P˙blico 94/95; Folha94/95












DOMAIN-SPECIFIC mono- and bilingual tasks






















iCLEF (to be communicated)















  Flikr images







QAatCLEF (choice of collection depends on task)

Sega;Standart (2002)

Frankfurt.R, Der Spiegel & SDA (94/95) 

LA Times, Glasgow Herald (94/95)

EFE (94/95)

  Aamulehti 94/95 

  LeMonde 94/95; SDA 94/95

La Stampa 94;SDA 94/95


NRC Handelsblad, Algemeen Dagblad (94/95)

 P˙blico 94/95; Folha94/95





Collection from Wikipedia  






IMAGE-CLEF (depending on task)












    Photo IR

Medical IR

Medical Annotation

Non-Medical Annotation















EN and/or CS
















see WebCLEF website

GeoCLEF (choice of collection depends on task)


  Frankfurt.R, Der Spiegel & SDA (94/95) 

LA Times, Glasgow Herald (94/95)

EFE (94/95)





  P˙blico 94/95; Folha94/95









End-User Agreement

The End-User Agreement must be submitted in two original signed copies.  Even if you have already participated in a CLEF campaign and have access to some of the data, you must have this form (in two copies) compiled and signed by the appropriate person in your organisation in order to be authorised to continue to use the data for CLEF 2006. You should indicate on this form only the data sets you need, depending on the tasks that you intend to perform. On receipt of the two copies of this form, they will both be signed on behalf of CLEF, and one will be kept in our archives and the other will be returned to you.

NIST Data Release Forms for American-English Data

The conditions to use the Los Angeles Times collection are unaltered from previous campaigns. You only need to complete these Data Agreement forms if you have not already been granted access to this data. Please note that only the Organisation Application must be sent to me; the Individual Application is to be kept by your organisation.

Organisation Application

Individual Application

Multilingual Document Collection

News Documents

The CLEF document collection consists of SGML or XML-formatted documents from national newspapers,  journals and news agencies from the same time period (1994 and 1995), as follows:
Dutch: NRC Handelsblad - 1994, 1995; Algemeen Dagblad - 1994, 1995
English: Los Angeles Times - 1994; The Herald -1995
Finnish: Aamulehti - 1995 (+small amount of 94 data);
French: Le Monde - 1994, 1995; SDA French Swiss news agency data - 1994, 1995
German:  Frankfurter Rundschau - 1994, 1995; Der Spiegel - 1994; SDA German Swiss news agency data - 1994, 1995
Italian: La Stampa - 1994; SDA Italian Swiss news agency data - 1994, 1995
Portuguese: P˙blico (Portuguese newspaper)- 1994, 1995; Folha - 1994; 1995 (Brazilian newspaper - under negotiation)
Russian: Izvestia - 1995
Spanish: Agencia EFE S.A. (Spanish news agency data) - 1994, 1995
Swedish: Tidningarnas Telegrambyrň -1994, 1995

plus the following newspapers for 2002
Bulgarian: Sega - 2002; Standart - 2002
Hungarian: Magyar Hirlap - 2002

Domain-Specific Collection
GIRT4 (German Indexing and Retrieval Testdatabase)
RSSC (Russian Social Science Corpus)

Image Collections
ImageCLEFmed Radiological Medical Database
IRMA Database of Medical Images

IAPR Database of photographs
LTU Database

Web Collection
EuroGOV - web documents crawled from European governmental sites

Spoken Documents
MALACH Collection spontaneous conversational speech from the Shoah archives: transcriptions in English and Czech

Access to the Data

When you have submitted the Registration and Data Release forms you will be given the necessary passwords to access the data and participation guidelines in the Workspace for Registered Participants.


The topic/question sets will be made accessible in the Workspace for Registered Participants, from 15 March on. Topics will be prepared in a number of languages depending on the task. Please refer to track/task descriptions. Other languages may be added depending on demand.


We gratefully acknowledge the support of all the data providers and copyright holders, and in particular:

Without their help, this evaluation activity would be impossible.

Please mail all forms by express or priority post to the address below. Access to the data will be provided only on receipt of the relevant forms.

Carol Peters - CLEF Coordinator
Area della Ricerca CNR 
Via Moruzzi, 1 - 56124 Pisa, Italy 
Fax: +39 050 315 3464/2810   Tel: +39 050 315 2897