Appel: CLEF, Call for participation INEX Tweet Contextualization track

Thierry Hamon thierry.hamon at UNIV-PARIS13.FR
Sat Mar 10 09:36:06 UTC 2012

Date: Fri, 09 Mar 2012 14:54:09 +0100
From: Veronique Moriceau <moriceau at>
Message-ID: <4F5A0B81.3080304 at>

*Call for participation*

*Tweet Contextualization *

an INEX Lab at CLEF 2012, 17--20 September in Rome, Italy

Participants are solicited for the *tweet contextualization* INEX task
at CLEF 2012. The use case of this new task is the following: given a
new tweet, the system must provide some context about the subject of the
tweet, in order to help the reader to understand it. This context should
take the form of a *readable summary, not **exceeding 500 words,
composed of passages from a provided Wikipedia corpus*. For more
information visit

The results of the evaluation campaign will be disseminated at the final
workshop which will be organized in conjunction with the CLEF 2012
conference, 17--20 September in Rome, Italy.

*Test data*

About 1000 tweets in English will be collected by the organizers from
Twitter®. They will be selected among informative accounts (for example,
@CNN, @TennisTweets, @PeopleMag, @science...), in order to avoid purely
personal tweets that could not be contextualized. Information such as
the user name, tags or URLs will be provided. The tweets will be made
available in a JSON format.

The document collection is a recent dump of the English Wikipedia
(November 2011). Since we target non factual answers but short
contextualizing texts, we removed all the info box and the external
references, leaving only the textual content with all its document
structure (title, abstract, sections, subtitles and paragraphs) and its
internal references (links towards other pages).

*Evaluation *

The summaries will be evaluated according to:

- the way they overlap with relevant passages (number of them,
  vocabulary and bi-grams included or missing),

- the readability assessed by evaluators and participants.


*March, 1 2012 *Online Registrations to the Labs opens *
March, 26 2012 *Test set release. *
June, 1 2012 *Run submissions. *
June, 30 2012 *Release of manual evaluation of readability by
participants. *
July, 15 2012 *Results to participants. *
August 17 2012 *Submission of CLEF 2012 Working Notes papers *
August 24 2012 *Submission of CLEF 2012 Labs Overviews *
September 17-20 2012 *CLEF 2012 Conference

*Organizers (contact : contextweet at*

Patrice Bellot, LSIS - Aix-Marseille University
Josiane Mothe, IRIT, University of Toulouse
Véronique Moriceau, LIMSI-CNRS, University Paris-Sud
Eric SanJuan, LIA, University of Avignon
Xavier Tannier,* *LIMSI-CNRS, University Paris-Sud

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

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

More information about the Ln mailing list