[Corpora-List] Call for papers: ACL 2007 Workshop - A Broader Perspective on Multiword Expressions

Stefan Evert stefan.evert at uos.de
Fri Feb 2 16:03:01 UTC 2007


######################################################################## 
###########
                  WORKSHOP ANNOUNCEMENT AND CALL FOR PAPERS

           ACL2007 - A Broader Perspective on Multiword Expressions

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


Date:      June, 28 (AM), 2007
Location:  Prague, Czech Republic

Workshop web page: http://www.let.uu.nl/~Nicole.Gregoire/personal/ 
ACL07-MWE/
######################################################################## 
###########

In recent years, the NLP community has increasingly become aware of  
the problems that multiword expressions (MWEs) pose. A considerable  
amount of research has been conducted in this area, some within large  
research projects dedicated to MWEs. Although progress has been made  
especially in the area of multiword extraction, a number of  
fundamental questions remain unanswered.

Following up workshops on various aspects of MWEs at previous ACL  
conferences, we want to address these questions in this year's MWE  
workshop:

- Is it sufficient to use purely statistical methods for the  
extraction of MWEs from corpora, or is it necessary to harness human  
knowledge and linguistic insights?
- Is fully automatic MWE extraction feasible, or will manual  
validation always be required?
- What is the nature of MWEs, and how can they be defined formally?
- To what extent can definitions and extraction procedures be  
generalised to other languages, other text types and other types of  
MWEs?
- Can and should we distinguish subtypes of MWEs for NLP applications?

In addition to these fundamental issues, we want to address the  
practical question of what is needed for a successful treatment of  
MWEs in NLP:

- What properties should be specified for MWEs or subtypes of MWEs in  
the lexicon?
- Can we detect these properties automatically with sufficient accuracy?
- How can existing grammars be adapted in order to deal better with  
MWEs?
- What role do the semantics of MWEs play in NLP applications and can  
they be determined automatically from large corpora?

We therefore solicit papers describing linguistically motivated  
approaches to MWEs, comparative studies across languages or different  
subtypes of MWEs, and the treatment of MWEs in NLP applications. This  
includes (but is not limited to) research on:

- Linguistic, Empirical and Cognitive Properties of MWEs: research  
into the definitions and characteristic properties of MWEs and the  
impact that such information has on NLP applications.

- Classes of MWEs: investigating classes (or subtypes) of MWEs and  
the extent to which computational techniques transfer to different  
classes and different languages.

- Linguistic and Psycholinguistic Theories of MWEs: combining the  
computational treatment of a class of MWEs with a solid linguistic  
and/or psycholinguistic analysis.


SUBMISSION INFORMATION

Submissions should follow the two-column format of ACL proceedings  
and should not exceed eight (8) pages, including references.

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) ...".

Submission will be electronic, using the workshop's START paper  
submission webpage (http://www.softconf.com/acl07/ACL07-WS6/ 
submit.html). The only accepted format for submitted papers is Adobe  
PDF. The papers must be submitted no later than 7pm US
Eastern time March 26, 2007 (23:59 GMT March 26, 2007). Papers  
submitted after that time will not be reviewed.


WORKSHOP FORMAT

This is a half-day workshop. The accepted papers will be presented as  
20-minute talks followed by a 10-minute discussion.


IMPORTANT DATES

Paper submission deadline: March 26, 2007
Notification of acceptance: April 30, 2007
Camera ready papers due: May 9, 2007
Workshop date: June 28 (AM), 2007


PROGRAM COMITTEE

Iñaki Alegria		(University of the Basque Country)
Timothy Baldwin	(Stanford University, USA; University of Melbourne,  
Australia)
Colin Bannard		(Max Planck Institute, Germany)
Francis Bond		(NTT Communication Science Laboratories, Japan)
Beatrice Daille		(Nantes University, France)
Gael Dias			(Beira Interior University, Portugal)
James Dowdall	(University of Sussex, UK)
Uli Heid			(Stuttgart University, Germany)
Kyo Kageura		(University of Tokyo, Japan)
Anna Korhonen	(University of Cambridge, UK)
Brigitte Krenn		(OFAI, Vienna, Austria)
Dan Moldovan		(University of Texas, USA)
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, USA)
Jan Odijk			(University of Utrecht, The Netherlands)
Stephan Oepen	(Stanford University, USA; University of Oslo, Norway)
Darren Pearce		(University of Sussex, UK)
Scott Piao		(University of Manchester, UK)
Violeta Seretan	(University of Geneva, Switzerland)
Suzanne Stevenson	(University of Tuebingen, Germany)
Beata Trawinski	(University of Toronto, Canada)
Kiyoko Uchiyama	(Keio University, Japan)
Ruben Urizar		(University of the Basque Country)
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

Su Nam Kim
University of Melbourne, Australia


CONTACT

For any inquiries regarding the workshop please contact Nicole Grégoire
(Nicole.Gregoire at let.uu.nl).



More information about the Corpora mailing list