[Corpora-List] Call for Papers - MWE 2008 Workshop

[Stefan Evert]

################################################################

  CALL FOR PAPERS

 >> LREC2008 - Towards a Shared Task for Multiword Expressions (MWE  
2008) <<

  endorsed by the ACL Special Interest Group on the Lexicon (SIGLEX)


Date: Sunday, 1 June 2008
Location: Marrakech, Morocco
Deadline: Friday, 29 February 2008

Workshop web page: http://multiword.sf.net/mwe2008/

#################################################################

In recent years, considerable progress has been made in our  
understanding of
multiword expressions (MWE), the development of algorithms for their  
automatic
extraction from corpora, and the automatic identification of additional
properties such as morphosyntactic preferences or the interpretation of
semi-compositional expressions.

It is difficult to compare results of the many published studies on  
MWEs and
obtain a broader perspective, though, because algorithms and implemented
systems have been evaluated on vastly different gold standards and  
corpora, in
different languages, for different subtypes of MWEs, etc. In order to  
make the
next big step forward, the field of MWE research needs a shared task  
in which
different approaches are applied to the same data sets, allowing  
completely
new insights to be gained. Since there is as yet not a clear and  
universally
accepted definition of multiword expressions, the first instalment of  
this
shared task will be of a more exploratory nature than the  
competitions that
have been carried out in other areas of computational linguistics.

The MWE 2008 workshop is primarily intended as a forum for  
collecting, sharing
and exploiting MWE evaluation resources. We have solicited  
contributions of
such resources in a separate call.

After collection of the resources, teams are invited to participate in a
shared task by evaluating their MWE extraction algorithms on data sets
downloaded from http://multiword.sf.net/. Further instructions will  
be made
available on the workshop web site, and the full collection of data  
sets will
be online by February 1, 2008 at the latest.

There will be three different types of submissions to the workshop:

(1) short papers describing data sets and other evaluation resources  
made
     freely available on the community Web page;

(2) shared task participants, who evaluate an algorithm or MWE  
extraction
     system on multiple data sets and discuss implications of their  
results;

(3) regular papers addressing the evaluation and comparison of multiword
     extraction algorithms (but not limited to these topics).

With this call, we invite submissions of REGULAR PAPERS, in particular
(but not limited to) research on:

(a) Linguistic analysis of MWEs based on language resources (such as  
corpora)
and the impact that these studies have on NLP applications.  We  
particularly
welcome papers that perform a cross-linguistic analysis of MWEs,  
identify
variation across languages, text types, domains, etc. or investigate the
variability of MWEs.

(b) Typologies of MWEs: Papers that describe classes of MWEs and their
representation in language resources, discuss different approaches to  
the
definition and classification of MWEs, or apply new MWE typologies to  
the
evaluation of computational techniques.

(c) The evaluation and comparison of multiword extraction techniques: Do
methods generalise across languages, text types, different classes of  
MWEs,
etc.? How useful and essential is linguistic knowledge and a theoretical
understanding of MWEs? Is fully automatic extraction feasible or will  
manual
intervention always be necessary?

(d) Evaluation methodology and the creation of gold standards for  
MWEs. Papers
should address theoretical and technical issues, while descriptions of
existing resources may be submitted as short papers for the shared task.
Topics of particular interest are novel types of gold standards (such  
as human
ratings from expert and non-expert subjects, language resources  
derived from
the Web, etc.), inter-annotator agreement in the manual validation of
candidate lists (which is often fairly low) and the task-based  
evaluation of
MWE resources in NLP applications.


SUBMISSION INFORMATION

Regular papers must adhere to the format of LREC proceedings  
(preferably using
the style files provided on the conference Web site) and must not exceed
eight (8) pages, including references. Short papers describing  
evaluation
resources and shared task participants will be allowed four (4)  
pages, using
the same formatting. Only submissions in PDF format will be considered.

As reviewing will be blind, the paper should not include the authors'  
names and
affiliations. Furthermore, self-citations and other references (e.g.  
to projects,
corpora, or software) that could reveal the author's identity should  
be avoided. For
example, instead of "We previously showed (Smith, 1991) ...", write  
"Smith previously
showed (Smith, 1991) ...".

The papers must be submitted no later than 23:59 GMT on February 29,  
2008.
Papers submitted after that time cannot be reviewed.

Please submit your paper here: https://www.softconf.com/LREC2008/ 
MWE2008/submit.html


IMPORTANT DATES

Paper submission deadline: February 29, 2008
Notification of acceptance: March 28, 2008
Camera ready papers due: April 4, 2008
Workshop date: June 1, 2008


PROGRAM COMITTEE

Iñaki Alegria, University of the Basque Country (Spain)
Timothy Baldwin, Stanford University (USA); U of Melbourne (Australia)
Colin Bannard, Max Planck Institute (Germany)
Francis Bond, NTT Communication Science Laboratories (Japan)
Gaël Dias, Beira Interior University (Portugal)
Ulrich Heid, Stuttgart University (Germany)
Kyo Kageura, University of Tokyo (Japan)
Rosamund Moon, University of Birmingham (UK)
Diana McCarthy, University of Sussex (UK)
Eric Laporte, University of Marne-la-Vallee (France)
Preslov Nakov, University of California, Berkeley (USA)
Jan Odijk, University of Utrecht (The Netherlands)
Stephan Oepen, Stanford University (USA); U of Oslo (Norway)
Darren Pearce, University of Sussex (UK)
Pavel Pecina, Charles University (Czech Republic)
Scott Piao, University of Manchester (UK)
Violeta Seretan, University of Geneva (Switzerland)
Suzanne Stevenson	University of Toronto (Canada)
Beata Trawinski, University of Tuebingen (Germany)
Kiyoko Uchiyama, Keio University (Japan)
Begoña Villada Moirón, University of Groningen (The Netherlands)
Aline Villavicencio, Federal University of Rio Grande do Sul (Brazil)


WORKSHOP CHAIRS

Nicole Grégoire
University of Utrecht, The Netherlands

Stefan Evert
University of Osnabrueck, Germany

Brigitte Krenn
Austrian Research Institute for Artificial Intelligence (ÖFAI), Austria


CONTACT

For any inquiries regarding the workshop please contact Nicole Grégoire
(Nicole.Gregoire at let.uu.nl).
_______________________________________________
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora