[Corpora-List] ACL Workshop on Multiword Expressions - 2nd Call for Papers

Stefan Evert stefan.evert at uos.de
Tue Mar 13 17:23:01 CET 2007


########################################################################
###########
2nd CALL FOR PAPERS

ACL 2007 Workshop

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

Submission deadline: 26 March 2007
Workshop Website: 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-archive mailing list