|
CLEF 2001 - INFORMATION FOR PARTICIPANTS Procedure Those wishing to take part in
CLEF 2001 should send an e-mail to Carol Peters (carol@iei.pi.cnr.it),
indicating in which task(s) they intend to participate (see Task Description for 2001)
and then compile and submit the appropriate Data Agreement forms (see below).
Multilingual Test Collection The main test collection for CLEF 2001
consists of SGML-formatted documents from national newspapers and journals and news agency documents
for English, French, German, Italian, Spanish, Dutch from the same time period:
The domain-specific collection consists of a structured database of
nearly 80,000 social science documents in German, known as GIRT. A German/English/Russian thesaurus and English translations of the
document titles are available.
Data Release Forms In order to have access to the test collections, the relevant data release agreement forms must be first compiled, signed, and sent (by express mail) to Carol Peters at the address below. On receipt of the forms, you will be sent information on how to download the data. For copyright reasons, you must fill out 2 sets of forms: 1 for the English data; the other covers Dutch, French, Italian, Spanish and German - including GIRT - data. Please indicate clearly which task(s) you will be performing as we are only authorised to provide data to those who are actually going to use it in CLEF. N.B.:
Please note that while the English data collection is the same as last year's,
the collections for the other languages are new - or have been enlarged.
Thus, if you already have the right to use and access to the LA Times data you do not
need to submit a Data Release form for this collection, but all participants must
complete the Data Release Forms for the other collections.
Everyone should fill in the
CLEF 2001 Agreement concerning
Dissemination of CLEF Results. The Organisation Applications should be
sent to the CLEF Coordinator at the address indicated. The Individual Applications
should be sent to and conserved by their Organisation. The Organization will retain
the applications of all persons ever granted access
to the information and make them available upon request by or on behalf of
any of the copyright
holders.
Data Release
Forms for English Data Organisation Application Individual Application
Data Release Forms for Dutch, French, German, Italian, Spanish Data Organisation Application Individual Application
Access to the Data When you have submitted the Data Agreement forms and have the necessary password(s), data can be downloaded here. You will also be able to access the "Guidelines for Participation" in the Working Area for Active Participants. Topics The topic set will be available in seven main languages (Dutch, English, French, German, Italian, Spanish and Japanese) and additional languages (possibly Greek, Finnish, Swedish and Russian) in the Working Area for Active Participants, from 9 April. Acknowledgments 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.
Contact Carol
Peters - IEI-CNR |