Subject: Coling-ACL'98: Discourse Relations and Discourse Markers, Partially Automated Techniques for Transcribing Naturally Occurring, Continuous Speech
From: Priscilla Rasmussen <rasmusse@cs.rutgers.edu>
To: elsnet-list@cogsci.ed.ac.uk
Date: Wed, 4 Mar 98 14:41:58 EST


Below are two more Coling-ACL'98 Workshop announcements:

-Discourse Relations and Discourse Markers
-Partially Automated Techniques for Transcribing Naturally 
 Occurring, Continuous Speech

seperated by:

**************************************************************************

Call for papers

                             Coling-ACL '98 workshop

                   "Discourse Relations and Discourse Markers"

                                August 15, 1998
                             Université de Montréal
                                Montréal/Canada

(See also: http://flp.cs.tu-berlin.de/~marker/aclcolingws.html)

The notion of discourse relation has received many different
interpretations, some of which are hardly compatible with one
another. Nonetheless, there is a consensus among researchers that
intersegment relations hold between adjacent portions of a text and
that these relations may be signalled by linguistic means, including
so-called cue phrases, aspect and mood shifts, theme inversions, and
other markers.

The workshop intends to bring together researchers working on
discourse relations and discourse markers in different linguistic
traditions and different NLP applications. The particular focus of the
workshop is the issue of discourse relations from the viewpoint of
linguistic realization. Specifically, contributions should address one
or more of the following questions:

o What are sound methodologies for comparing similar discourse markers
(contrastive studies, distribution analyses, etc.)?

o What are sound methodologies for relating discourse relations with
potential realizations?

o Are there discourse relations that are always lexically signalled?
Are there any that are never lexically signalled?

o What non-lexical (i.e., syntactic or prosodic) means are used to
signal a relation?

o In production, how does one decide whether to signal a relation at
all?

o In production, how does one motivate a choice among candidate
signals for a given relation?

o In production, how does the choice of signal interact with other
decisions (in particular, those of linearizing some tree or graph
structure)?  

o In analysis, is it possible to reliably infer discourse relations
from surface cues?  

o In analysis, how can one disambiguate polysemous signals such as
"and", "since" (temporal or causal) etc.?

o What are useful lexical representations of discourse markers, for
both analysis and production?  

o What are useful representations of discourse relations (and the
entities they relate), such that they facilitate the realization
decision? What features would one like to have handy in a
representation so that choices can be made easily?

o Are there significant differences between realizations in spoken and
written language?  

o How do individual languages differ in terms of any of the above
issues?



Organizing committee 

The workshop is organized by 

      Manfred Stede (TU Berlin)
      Leo Wanner (University of Stuttgart)
      Eduard Hovy (ISI/USC, Marina del Rey) 



Requirements for submission

      Papers are invited that address any of the topics listed above.
      Maximum length is 8 pages including figures and references.
      Please use A4 or US letter format and set margins so that the
      text lies within a rectangle of 6.5 x 9 inches (16.5 x 23 cm).
      Use classical fonts such as Times Roman or Computer Modern, 11
      to 12 points for text, 14 to 16 points for headings and title.
      LaTeX users are encouraged to use the style file provided by
      ACL: http://coling-acl98.iro.umontreal.ca/colaclsub.sty Papers
      can be submitted either electronically in PostScript format, or
      as hardcopies.

Submissions from North America should be sent to: 

Eduard Hovy
Information Sciences Institute 
4676 Admiralty Way Marina del Rey, CA 90292-6695 
U.S.A. 
hovy@isi.edu

Submissions from elsewhere should be sent to either of the following: 

Manfred Stede                 Leo Wanner
TU Berlin                     Computer Science Department
KIT Project Group             Intelligent Systems Group
Sekr. FR 6-10                 University of Stuttgart
Franklinstr. 28/29            Breitwiesenstr. 20-22
D-10587 Berlin                D-70565 Stuttgart
Germany                       Germany
stede@cs.tu-berlin.de         wannerlo@informatik.uni-stuttgart.de



Timetable

Deadline for electronic submissions: March 10, 1998 
Deadline for hardcopy submissions: March 13 (arrival date) 
Notification of acceptance: May 1, 1998 
Final manuscripts due: June 12, 1998 



Program committee

      Sandra Carberry (U Delaware) 
      Barbara DiEugenio (U Pittsburgh) 
      Eduard Hovy (USC/ISI) 
      Alistair Knott (U Edinburgh) 
      Alex Lascarides (U Edinburgh) 
      Owen Rambow (Cogentex Inc.) 
      Ted Sanders (U Utrecht) 
      Donia Scott (U Brighton) 
      Wilbert Spooren (U Tilburg) 
      Manfred Stede (TU Berlin) 
      Keith Vander Linden (Calvin College) 
      Marilyn Walker (ATT Labs) 
      Leo Wanner (U Stuttgart) 

****************************************************************************

 	 CALL FOR PAPERS   CALL FOR PAPERS   CALL FOR PAPERS


                           ACL/COLING-98

                            Workshop on

           PARTIALLY AUTOMATED TECHNIQUES FOR TRANSCRIBING
                 NATURALLY OCCURRING, CONTINUOUS SPEECH

              August 16, 1998 (following ACL/COLING-98)
          University of Montreal, Montreal (Quebec, Canada)


                          CALL FOR PAPERS



DESCRIPTION
-----------

The development of robust systems for speech analysis and synthesis
depends crucially on the availability of well-annotated corpora of
naturally occurring, continuous speech. Yet existing speech corpora
are rarely well-annotated. A key to proper annotation is the
availability of partially automated systems for linking selected
portions of a visual display of speech to the corresponding
transcriptions. To be of practical use, such systems must be able to
handle large files of digitized speech and they should permit
transcriptions at different levels of analysis.

     This workshop will be devoted to the presentation and discussion
of papers and software demonstrations which reflect the current state
of the art. We invite proposals of up to 800 words which address the
development, use, evaluation, or potential commercial application of
such systems.



SUBMISSIONS
-----------

Only email submissions in LaTeX or Ascii will be accepted.
Authors should submit an abstract of no more than 800
words to:

            trans98@cs.concordia.ca

Style files and templates for LaTeX submissions can be
found at

           http://colingacl98.iro.umontreal.ca/Styles.html

The official language of the conference is English.


IMPORTANT DEADLINES
-------------------

   Submission Deadline:   April 15, 1998
   Notification Date:     May 15, 1998
   Camera ready copy due: June 15, 1998


PROGRAM COMMITTEE
--------------------

   Nancy Belmore		Concordia University, Canada
   Sabine Bergler		Concordia University, Canada
   John Esling			Univ. of Victoria, Canada
   Eric Keller			Univ. of Lausanne, Switzerland
   Roland Kuhn			Panasonic Technologies, Inc., U.S.A.
   Douglas O'Shaughnessy	INRS-Telecommunications, Canada
   Ching Y. Suen		Concordia University, Canada

ORGANIZERS
----------

   Nancy Belmore		Concordia University, Canada
   Sabine Bergler		Concordia University, Canada
   Douglas O'Shaughnessy	INRS-Telecommunications, Canada


REGISTRATION
------------

There is a discounted workshop fee for participants of
Coling/ACL. Participants who are not registered for Coling/ACL will
have to pay the full workshop fee (to be announced shortly).



INFORMATION
-----------

Any requests for information should be sent to

   trans98@cs.concordia.ca