LINGUIST List 15.842

Thu Mar 11 2004

Calls: Computational Ling/Spain; Computational Ling

Editor for this issue: Andrea Berez <andrealinguistlist.org>


As a matter of policy, LINGUIST discourages the use of abbreviations or acronyms in conference announcements unless they are explained in the text. To post to LINGUIST, use our convenient web form at http://linguistlist.org/LL/posttolinguist.html.

Directory

  1. szpak, Text Summarization Branches Out
  2. karinem, Computational Approaches to Arabic Script-based Languages

Message 1: Text Summarization Branches Out

Date: Wed, 10 Mar 2004 20:23:04 -0500 (EST)
From: szpak <szpaksite.uottawa.ca>
Subject: Text Summarization Branches Out

Text Summarization Branches Out 

Date: 25-Jul-2004 - 26-Jul-2004
Location: Barcelona, Spain
Contact: Stan Szpakowicz
Contact Email: szpaksite.uottawa.ca 
Meeting URL: http://www.law.kuleuven.ac.be/icri/conferences/acl_summarization2004.php 

Linguistic Sub-field: Computational Linguistics 

Call Deadline: 25-Mar-2004 


Meeting Description:

Text Summarization Branches Out
July 25-26, 2004.

Workshop at ACL 2004, 42nd Annual Meeting of the Association for
Computational Linguistics Forum Convention Centre, Barcelona, Spain

http://www.law.kuleuven.ac.be/icri/conferences/acl_summarization2004.php


Second call for papers

Text summarization is still largely in a research phase, and has so
far focused on news text, but it is increasingly becoming a tool for
information search and selection in a variety of media. For example,
summarizing is a necessity when showing content on the screen of a
mobile device. Texts integrated in multimedia documents have different
genres or types, but they all require the same flexibility in the
presentation of summaries by allowing parameterized compression rates
and integration in a mixed media format.

Text summarization has been so far dominated by statistical
techniques. However, for improved output quality and increased
compression, other techniques are expected to play important roles as
well. Linguistically motivated natural language processing techniques,
including semantic analysis and discourse analysis, are almost
certainly required for summarization in non-news genres. Automated
reasoning techniques could allow fusion and understanding of
content. Machine learning, both supervised and unsupervised, still has
a major role to play. Finally, evaluation is an ongoing concern. The
proposed workshop aims to address all these issues.

We invite submission of papers about text summarization including, but
not limited to, the following topics.

* Single-sentence compression
* Multiple-sentence compression and information fusion
* Domain-oriented summarization of multiple texts
* Comparative summarization of multiple reviews
* Summarization of Web pages
* Summarization of dialogue (e.g., blogs, video captions)
* Summarization of speech
* Summarization for mobile devices
* Summarization for other disciplines, e.g., legal or medical
applications
* Toward summarizing large, loosely structured texts (e.g., novels)
* Temporal and event semantics for summarization
* Data search structures for summaries of flexible and mixed media
format
* Automated and manual summary evaluation methods
* Quantifying summary quality

The workshop will feature an invited speaker (to be confirmed), and
two panels, one looking back and one looking far ahead, plus ad-hoc
discussion groups.

Important Dates

* Paper submission deadline: March 25, 2004
* Notification of acceptance for papers: April 25, 2004
* Camera ready papers due: May 15, 2004
* Workshop date: July 25-26, 2004

Submission Procedure

Authors should submit full papers of maximum 8 pages, including
references and figures, following the main conference ACL style
format. Submissions should be sent to:

http://www.law.kuleuven.ac.be/icri/cyber-chair/html/submit/


Organizing Committee

* Eduard Hovy, Information Sciences Institute, University of Southern
California, USA
* Marie-Francine Moens (co-chair), Interdisciplinary Centre for Law &
Information Technology, Katholieke Universiteit Leuven, Belgium
* Dragomir Radev, School of Information and Department of Electrical
Engineering and Computer Science, University of Michigan, USA
* Stan Szpakowicz (co-chair), School of Information Technology and
Engineering, University of Ottawa, Canada

Program Committee

* Regina Barzilay, Computer Science and Artificial Intelligence Lab,
MIT, USA
* Hercules Dalianis, Royal Institute of Technology, Sweden
* Chiori Hori, NTT, Japan
* Eduard Hovy, Information Sciences Institute, University of
 Southern California, USA
* Hongyan Jing, IBM T.J. Watson Research Center, USA
* Kathy McKeown, Computer Science Department, Columbia University, USA
* Chin-Yew Lin, Information Sciences Institute, University of Southern
California, USA
* Inderjeet Mani, Department of Linguistics, Georgetown University,
USA
* Daniel Marcu, Information Sciences Institute, University of Southern
California, USA
* Marie-Francine Moens, Interdisciplinary Centre for Law & Information
Technology, Katholieke Universiteit Leuven, Belgium
* Dragomir Radev, School of Information and Department of Electrical
Engineering and Computer Science, University of Michigan, USA
* Horacio Rodriguez, Departamento de LSI, Universitat Politecnica de
Catalunya, Spain
* Horacio Saggion, Department of Computer Science, University of
Sheffield, UK
* Judith Schlesinger, IDA/Center for Computing Sciences, USA
* Karen Sparck Jones, Computer Laboratory, University of Cambridge, UK
* Stan Szpakowicz, School of Information Technology and Engineering,
University of Ottawa, Canada
* John Tait, School of Computing and Technology, University of
Sunderland, UK
* Simone Teufel, Computer Laboratory, University of Cambridge, UK
* Peter Turney, NRC Ottawa, Canada
* Hans van Halteren, Department of Language and Speech, University of
Nijmegen, The Netherlands

Contact addresses

Marie-Francine Moens
Interdisciplinary Centre for Law & Information Technology
Katholieke Universiteit Leuven
Tiensestraat 41
B-3000 Leuven
Belgium
marie-france.moenslaw.kuleuven.ac.be
http://www.law.kuleuven.ac.be/icri/staff/staff.php?id=13

Stan Szpakowicz
School of Information Technology and Engineering
University of Ottawa
800 King Edward Avenue
Ottawa, Ontario
K1N 6N5
Canada
szpaksite.uottawa.ca
http://www.site.uottawa.ca/~szpak 
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue

Message 2: Computational Approaches to Arabic Script-based Languages

Date: Thu, 11 Mar 2004 10:01:54 -0500 (EST)
From: karinem <karineminxight.com>
Subject: Computational Approaches to Arabic Script-based Languages

Computational Approaches to Arabic Script-based Languages 
Short Title: coling2004 workshop 

Date: 28-Aug-2004 - 28-Aug-2004
Location: Geneva, Switzerland
Contact: Karine Megerdoomian
Contact Email: karineminxight.com 
Meeting URL: http://members.cox.net/karinem/COLING2004 

Linguistic Sub-field: Computational Linguistics 
Subject Language: Arabic, Standard ,Kurdi ,Pashto, Southern ,Farsi,
Western ,Urdu

Call Deadline: 25-Mar-2004 
This is a session of the following conference: 20th International
Conference on Computational Linguistics

Meeting Description:

Recently, there has been a surge of interest in the study of the
languages of the Middle East, especially Arabic, Persian (Farsi),
Pashto and Urdu. Computational applications for proper name
identification, entity recognition, categorization, information
retrieval, summarization, machine translation and other
implementations are currently in high demand. The goal of this
workshop, being held as a session of COLING 2004, is to provide a
forum for those involved in the development of NLP systems in Arabic
script languages to exchange ideas, approaches and implementations of
computational systems; to discuss the common challenges faced by all
practitioners; and to assess the state of the art in the field.
SECOND CALL FOR PAPERS

		COLING 2004 WORKSHOP ON
COMPUTATIONAL APPROACHES TO ARABIC SCRIPT-BASED LANGUAGES

		Geneva, Switzerland, 23-27 August 2004
	 http://members.cox.net/karinem/COLING2004


WORKSHOP DESCRIPTION

Recently, there has been a surge of interest in the study of the
languages of the Middle East, especially Arabic, Persian (Farsi),
Pashto, Kurdish and Urdu. This sudden and urgent interest is
manifested by the availability of funding for rapid development of
practical systems for processing large volumes of data in these
languages. Computational applications for proper name identification,
entity recognition, categorization, information retrieval,
summarization, machine translation and other implementations are
currently in high demand. This comes at a time when advances in formal
and computational linguistics over the last fifty years are being
consolidated, while work on machine learning and statistical methods
has been showing great promise.

Although there exists a considerable body of work in computational
linguistics specifically targeted to these middle eastern languages,
much of the research and development has been the result of
initiatives by individual research establishments or industry
firms. Furthermore, the usage of the Arabic script gives rise to
certain issues that are common to all these languages despite their
being of distinct language families. Hence, these languages share
properties such as the absence of capitalization, right to left
direction, lack of clear word boundaries, complex word structure, a
high degree of ambiguity due to non-representation of short vowels in
the writing system, and related encoding issues.

The goal of this workshop is to provide a forum for those involved in
the development of NLP systems in Arabic script languages to exchange
ideas, approaches and implementations of computational systems; to
discuss the common challenges faced by all practitioners; and to
assess the state of the art in the field. In addition, one of the aims
of the workshop is to identify promising areas for future
collaborative research in the development of NLP systems for Arabic
script languages. Solutions that are designed to solve the specific
problems of these languages could very well have wider applications
and relevance to the rest of the NLP community.


WORKSHOP TOPICS

Authors of papers in any area of NLP in Arabic script-based languages
are encouraged to apply. We encourage submissions dealing with
language-specific issues, as well as discussions of challenges imposed
by the usage of the Arabic script. Papers dealing with various
methodologies such as statistical approaches, shallow parsing and
linguistic-based analyses are encouraged. Submissions could also be on
- but not limited to - any of the following topics:

* Morphological analysis
* Syntactic ambiguity resolution
* Machine translation from and to Arabic script languages
* Sense disambiguation
* Homograph resolution
* Semantic analysis
* Entity recognition
* Information retrieval
* Classification of documents
* Text mining
* Summarization
* Speech recognition and generation
* Lexical databases
* Knowledge and domain representation
* Spelling and grammar checking tools

Proposals for formal demonstrations of advanced operational systems as
well as research prototypes are welcome.


SUBMISSION REQUIREMENTS

Papers should be original, previously unpublished work and should not
identify the author(s). They should be no longer than 8 pages
(including figures and references) and should emphasize completed work
rather than intended work. Papers that are being submitted to other
conferences must reflect this fact on the title page. Submissions are
limited to one individual and one joint paper per author.

Demonstration proposals should give a short description of the system,
provide its technical specifications and indicate how the
demonstration illustrates new ideas and contributes to the
computational work on Arabic-script languages. The proposals are not
to exceed 4 pages.

Email submissions (ps or pdf) are preferred and should be sent to both
AliFarghalyaol.com and karineminxight.com. Submissions should be in
English. The papers should be attached to an email indicating contact
information for the author(s) and paper's title. The hardware,
software and network requirements for the system demonstrations should
also be indicated in the text of the email. Formatting requirements
for the final version of accepted papers will be posted as soon as
they become available.

Hardcopy submissions should be sent to:
Ali Farghaly
SYSTRAN Software, Inc.
9333 Genesee Ave, Pl 1
San Diego, CA 92121
USA


PROCEEDINGS AND WORKSHOP ORGANIZATION

Accepted papers and formal demonstrations will be published in a
proceedings volume. For the workshops to take place, the COLING 2004
organizers require at least 20 participants to register for the
workshop. Speakers and participants are therefore asked to register
via the official COLING 2004 site as soon as possible.


IMPORTANT DATES

Submissions due: March 25th, 2004
Notification date: April 25th, 2004
Deadline for camera ready copy: May 25th, 2004


ORGANIZING COMMITTEE

This workshop is organized by
Ali Farghaly (SYSTRAN Software, Inc.)
Karine Megerdoomian (Inxight Software and University of California San
Diego)

The call for papers as well as future information on the workshop can
be found at
http://members.cox.net/karinem/COLING2004


PROGRAM COMMITTEE

Jan W. Amtrup, Bowne Global Solutions
Tim Buckwalter, Linguistic Data Consortium
Miriam Butt, Konstanz University, Germany
Violetta Cavalli-Sforza, Carnegie Mellon University
Joseph Dichy, Lyon University
Abdel Kadir Fassi Fehri, Arabization Bureau, Rabat, Morocco
Andrew Freeman, University of Washington
Nizar Habash, University of Maryland, College Park
Masayo Iida, Inxight Software, Inc.
Simin Karimi, University of Arizona
Martin Kay, Stanford University
Kevin Knight, USC/Information Sciences Institute
Farhad Oroumchian, University of Wollongong in Dubai
Ahmed Rafea, The American University in Cairo
Jean Senellart, SYSTRAN Software
Bonnie Glover Stalls, University of Southern California
Remi Zajac, SYSTRAN Software
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue