Difference between revisions of "SIGGEN: Newsletter Archive"

From ACL Wiki
Jump to navigation Jump to search
 
(One intermediate revision by the same user not shown)
Line 3,356: Line 3,356:
  
 
http://logos.uwaterloo.ca/~inlg98
 
http://logos.uwaterloo.ca/~inlg98
 +
 +
===Issue 1===
 +
 +
Date: 2 Jan 1997
 +
----
 +
 +
 +
----
 +
 +
 +
TOPICS:
 +
 +
1. NEW! SIGGEN WEB SITE <http://www.cs.bgu.ac.il/siggen>
 +
 +
2. Contribute: workshop papers, thesis, siggen directory.
 +
 +
3. ELRA News
 +
 +
4. CFP: RIAO'97 Computer Assisted Information Searching On Internet
 +
 +
<p style="text-indent:1em">25 June 97, Montreal - Deadline March 3, 1997</p>
 +
 +
<p style="text-indent:1em"><mailto:Abdellatif.Saoudi(at)irin(dot)univ-nantes(dot)fr> </p>
 +
 +
5. NLP Research Positions in Sydney, Australia <rdale(at)mpce(dot)mq(dot)edu(dot)au>
 +
 +
6. CFP: EMNLP-2 (SIGDAT) - Deadline: March 3, 1997
 +
 +
<p style="text-indent:1em">August 1-2, 1997 (Immediately following AAAI-97) - Brown University</p>
 +
 +
7. CFP: EUROSPEECH 97 - Deadline: 1 February 1997
 +
 +
<p style="text-indent:1em">Rhodes, Greece, 22-25 September 1997</p>
 +
 +
8. CFP: BISFAI'97 - Deadline: February 2nd 1997
 +
 +
 +
June 16-18, 1997, Bar-Ilan University, Ramat-Gan, Israel
 +
----
 +
 +
 +
 +
 +
----
 +
 +
 +
Topic 1:
 +
 +
From: siggen(at)cs(dot)bgu(dot)ac(dot)il (Michael Elhadad)
 +
 +
Subject: SIGGEN Web site
 +
 +
Happy new year!  SIGGEN is finally moving to the era of the World Wide Web.
 +
 +
The SIGGEN Web site is:
 +
 +
<http://www.cs.bgu.ac.il/siggen>
 +
 +
 +
Please check it and contribute material to add there.  Send me all your
 +
 +
comments.  I have been thinking about adding a members directory.  I believe
 +
 +
the best way is if you want to have your name and http address added there with
 +
 +
a short description of your interests, please mail them to me and I will
 +
 +
maintain the directory (until someone contributes a program to do these things
 +
 +
automatically).
 +
 +
 +
From now on, I will add conference and workshop announcements on the Web site
 +
 +
and only send pointers in the newsletter (which will become much shorter).
 +
 +
 +
With the new year, feel free again to contribute to this newsletter: send
 +
 +
questions, update on your research, paper announcements, reaction on published
 +
 +
papers, reviews etc.
 +
 +
 +
The newsletter is sent approximately every two months.  If you want to remove
 +
 +
your name from the list, please send email to siggen(at)cs(dot)bgu(dot)ac(dot)il.
 +
 +
----
 +
 +
 +
Topic 2:
 +
 +
From: siggen(at)cs(dot)bgu(dot)ac(dot)il (Michael Elhadad)
 +
 +
Subject: Previous workshop papers
 +
 +
 +
Many people have observed that many Generation papers have appeared in one of
 +
 +
the previous Workshops on Generation.  These papers are difficult to find.  We
 +
 +
should make every effort to make them more available.  This is a call to all
 +
 +
authors of papers previously published in one of the Generation Workshops to
 +
 +
send to SIGGEN a pointer to the file(s) of the paper.
 +
 +
 +
The SIGGEN Web site also contains pointers to generation resources: papers,
 +
 +
thesis, software.  Contribute!
 +
 +
 +
----
 +
 +
 +
Topic 3:
 +
 +
 +
From: elra(at)calvanet(dot)calvacom(dot)fr (Khalid Choukri)
 +
 +
Subject: INFORMATION FROM ELRA (European Language Resources Association)
 +
 +
 +
                      <center>INFORMATION FROM THE </center>
 +
 +
            <center>European Language Resources Association    </center> 
 +
               
 +
                       
 +
                          <center>  ELRA News </center>
 +
 +
 +
ELRA (European Language Resources Association), was founded in Luxembourg in
 +
 +
February 1995, as a non-profit organization, with the goal of promoting the
 +
 +
creation, verification and distribution of Language Resources (LR). In addition
 +
 +
to helping users and developers, government agencies, and other interested
 +
 +
parties exploit language resources for a wide variety of use, ELRA serves as
 +
 +
the European repository for EU-funded language resources, and interact with
 +
 +
similar bodies in other parts of the world. Funded in the medium term by
 +
 +
membership fees, grants from the European Commission and national governments,
 +
 +
together with projects income, the Association will be financially
 +
 +
self-supporting in the long run. A 12-member Board is in charge of the strategy
 +
 +
and objectives to be adopted by the Association.
 +
 +
 +
Relevant LR are Spoken Databases, Lexica, Grammars, Written Corpora and
 +
 +
Terminological Data. These are required for the development of speech and text
 +
 +
processing systems for a large number of applications in various information
 +
 +
technology areas.
 +
 +
 +
ELRA licences LR for R&D, as soon as these are made available. According to the
 +
 +
agreements made between ELRA and its providers, resources can be either
 +
 +
reserved for research purposes or used for the development of products and
 +
 +
services. Licence agreements, drawn with the support of lawyers, are used for
 +
 +
negotiations. Such contracts are available at ELRA office. Lexica, Corpora
 +
 +
(spoken and written), Grammars and Tools are described in easy-to-understand
 +
 +
presentation forms. All these documents can be found on the ELRA Web site.
 +
 +
 +
                                  <center><u> ELRA Newsletters</u></center>
 +
                                 
 +
 +
A Newsletter is released by ELRA every Quarter. The next three issues will
 +
 +
primarily and alternatively be devoted to each of the 3 Colleges of the
 +
 +
Association : spoken, written and terminological resources. The October
 +
 +
Newletter (vol.1 n.3) is already available at ELRA office. It is entirely
 +
 +
dedicated to Terminology. The next two issues will be dedicated to written and
 +
 +
spoken resources.
 +
 +
                                <center><u> The ELRA Web site</u></center>
 +
                               
 +
 +
The ELRA Web site is now available in English and French. The URL addresses
 +
are:
 +
English version: <http://www.icp.grenet.fr/ELRA/home.html>
 +
 +
French version : <http://www.icp.grenet.fr/ELRA/fr/home.html>
 +
 +
 +
 +
                                <center><u>ELRA Language Resources catalogue </u></center>
 +
 +
 +
A catalogue of the LR negotiated or under negotiation by ELRA can be found on
 +
 +
our Web site. For quotation, please refer to this site or directly to ELRA
 +
 +
office. A published version is released twice a year (together with number 1
 +
 +
and 3 of the Newsletter).
 +
 +
 +
Resources appearing in the catalogue are separated according to the three
 +
 +
Colleges : spoken resources, written resources (corpora, lexica and tools) and
 +
 +
terminological resources. The catalogue consists of :
 +
 +
 +
1) Spoken resources : 30 databases (recordings from microphone, telephone,
 +
 +
continuous speech, isolated words, several languages, etc.).
 +
 +
 +
2) Written resources :
 +
 +
<p>*    9 monolingual and multilingual corpora </p>
 +
 +
    <p>*  12 monolingual lexica </p>
 +
 +
<p>*  Over 30 multilingual lexical </p>
 +
 +
<p>*  A linguistic software platform and Grammars Development platform </p>
 +
 +
 +
3) Terminological resources : over 90 databases with a wide range of domains
 +
 +
and several languages (French, English, German, Spanish, Danish, Italian,
 +
 +
Catalan, Turkish, Polish, Portuguese).
 +
 +
 +
                                    <center><u> ELRA Membership</u></center>
 +
                                     
 +
 +
ELRA members are entitled to substantial discounts on public prices of the
 +
 +
resources and other products (such as the Guide for Terminology Agreements and
 +
 +
several commercial reports).
 +
 +
 +
ELRA membership is open to any organization, public or private, with full
 +
 +
membership (including voting privileges) being available to organizations
 +
 +
registered in Europe. Purely for organizational purposes, members will be
 +
 +
assigned to one of the Colleges on the basis of their main area of
 +
 +
interest. The annual membership fee has been set at a modest ECU 1,000 to
 +
 +
encourage broad participation. You may also opt to join more than one College,
 +
 +
in which case you will be required to pay multiple membership fees.
 +
 +
 +
Please ask for a membership form or download it from the ELRA Web site.
 +
 +
 +
For further information :
 +
                        <center> ELRA/ELDA</center>
 +
 +
                          <center>87, Avenue d'Italie</center>
 +
 +
                          <center>FR-75013 PARIS </center>
 +
 +
                          <center>FRANCE </center>
 +
 +
 +
                          <center>Tel : +33 01 45 86 53 00</center>
 +
 +
                          <center>Fax : +33 01 45 86 44 88</center>
 +
 +
                          <center>E-mail : elra(at)calva(dot)net</center>
 +
 +
                          <center>http://www.icp.grenet.fr/ELRA/home.html</center>
 +
 +
----
 +
 +
 +
Topic 4:
 +
 +
From: Abdellatif.Saoudi(at)irin(dot)univ-nantes(dot)fr (Abdellatif Saoudi)
 +
 +
 +
                        <center>CALL FOR PAPERS</center>
 +
 +
                          <center>5TH RIAO CONFERENCE</center>
 +
 +
            <center> COMPUTER ASSISTED INFORMATION SEARCHING ON INTERNET</center>
 +
 +
 +
                      <center> 25th-27th June 1997</center>
 +
 +
          <center><u> McGill University, Montreal, Quebec H3A 2T7,Canada,</u></center>
 +
 +
 +
"RIAO 97" will be the fifth conference in the series. RIAO 85 took place in
 +
 +
France, RIAO 88 at MIT (Cambridge MA., U.S.A.), RIAO 91 in Barcelona, Spain,
 +
 +
and RIAO 94 in New York.  The Conference is organized by the "CENTRE DE HAUTES
 +
 +
ETUDES INTERNATIONALES D'INFORMATIQUE DOCUMENTAIRE" (CID) Paris.
 +
 +
 +
Facing the growth of document information available throught the Internet way
 +
 +
(Web sites, NewsGroups or emails), it is necessary to offer new technologies,
 +
 +
mechanisms and systems to manage all that information.  The huge amount of
 +
 +
information implies rapid indexing and retrieval engines, efficient datamining
 +
 +
and knowledge discovery systems in oder to find relevant or strategic
 +
 +
information.  On one hand,linguistic tools are necessary when managing textual
 +
 +
information ; one the other hand specifics problems have to be solved regarding
 +
 +
the management of multimedia information : multimedia information
 +
 +
characterisation, search mechanisms, multimedia interfaces.  Tools are also
 +
 +
necessary to deal with the diversity of the information source. Where is the
 +
 +
relevant information stored? Which are the best sources? How can heterogeneous
 +
 +
repositories be queried, ...?  Finally, the current ways of diffusing
 +
 +
information such as the Internet lead to security problems that must not be
 +
 +
overlooked.
 +
 +
 +
The purpose of this conference is to confront specialists in media contents
 +
 +
with specialists in Web-based searching.
 +
 +
 +
More specifically, papers are expected to cover one or more of the following
 +
 +
topics :
 +
 +
A - Rapid indexing and retrieval engines, automatic abstracting
 +
 +
B - Evaluation of linguistic tools in information retrieval
 +
 +
C - Information Retrieval from several repositories
 +
 +
<p style="text-indent:1em">- Identification of duplicated documents in different</p>
 +
 +
<p style="text-indent:1em">repositories (different languages, structures or versions),</p>
 +
 +
<p style="text-indent:1em"> - Unification of documents from heterogeneous repositories ;</p>
 +
 +
<p style="text-indent:1em">datawarehousing,</p>
 +
 +
<p style="text-indent:1em">- Interest of the use of datamining and knowledge discovery</p>
 +
 +
<p style="text-indent:1em">strategies when querying large repositories,</p>
 +
 +
<p style="text-indent:1em">- Evaluation of repository for a given search strategy.</p>
 +
 +
D - Technology watch techniques using strategy on the Web ;
 +
 +
content adressable electronic mail, news group, WWW systems.
 +
 +
E - Architecture
 +
 +
<p style="text-indent:1em">- How can large data flows be exploited by information retrieval tools,</p>
 +
 +
<p style="text-indent:1em">- Distributed, multi-agent architectures</p>
 +
 +
F - Image
 +
<p style="text-indent:1em"> - Image content characterisation, human and automatic image description methods,</p>
 +
 +
<p style="text-indent:1em">- Image search strategies</p>
 +
 +
G - Sound
 +
<p style="text-indent:1em"> - Sound content characterisation,</p>
 +
 +
<p style="text-indent:1em">- Automatic identification of sound type: speech, music...,</p>
 +
 +
<p style="text-indent:1em">- Spoken language recognition,</p>
 +
 +
<p style="text-indent:1em"> - Word-spotting.</p>
 +
 +
H - Content-based compression techniques
 +
 +
I - Multimedia interfaces : Iconic, navigational, speech interface
 +
 +
to web search
 +
 +
J - Data security problems: copyright protection, internet crime
 +
 +
K - Web-related international conventions and policies
 +
 +
 +
IMPORTANT DATES :
 +
 +
{|
 +
  |      Closing date for submission:|| 20 January 1997
 +
  |-
 +
  |      Notification of acceptance: || 10 March 1997
 +
  |-
 +
  |      Camera-ready copy:          ||10 May 1997
 +
  |-
 +
  |    Conference start-date:      ||25 June 1997
 +
|}
 +
 +
Detailed information regarding RIAO-97 can be found  on the World Wide
 +
 +
Web Server :
 +
 +
http://www.sciences.univ-nantes.fr/RIAO97/
 +
 +
 +
 +
----
 +
 +
 +
Topic 5:
 +
 +
From: Robert Dale <rdale(at)mpce(dot)mq(dot)edu(dot)au>
 +
 +
Subject: NLP Research Positions in Sydney, Australia
 +
 +
 +
Are you in the northern hemisphere? Chilly, huh? Well: why not carry
 +
 +
out research in language technology in Sydney, Australia ...
 +
 +
 +
The Microsoft Research Institute's Language Technology Group, situated
 +
 +
on the campus of Macquarie University in Sydney, is currently seeking
 +
 +
to hire two research scientists. The successful candidates will work
 +
 +
on a number of ongoing and new projects in the areas of natural
 +
 +
language processing and language engineering. We are particularly
 +
 +
interested in hiring people to work in the following three areas:
 +
 +
 +
automatic text generation;
 +
 +
intelligent text processing and information extraction; and
 +
 +
connecting language and action.
 +
 +
 +
Generally, we expect research staff to spend approximately 50% of
 +
 +
their time working on group projects, and 50% pursuing other research
 +
 +
avenues of their own devising. We are particularly interested in
 +
 +
candidates with previous experience in one or more of the following
 +
 +
areas:
 +
 +
 +
corpus-based and statistical methods;
 +
 +
message extraction and understanding;
 +
 +
the use of natural language processing techniques in information
 +
 +
retrieval; 
 +
 +
the design and development of dialogue systems;
 +
 +
text planning; and
 +
 +
linguistic realisation.
 +
 +
 +
Applicants should have a postgraduate degree in computational
 +
 +
linguistics, computer science or linguistics, and competence in
 +
 +
several areas drawn from the following portfolio:
 +
 +
 +
Computational linguistic theory: a basic understanding of parsing
 +
 +
techniques; a grounding in one or more syntactic theories; a
 +
 +
familiarity with techniques in statistical text processing; an
 +
 +
understanding of issues in discourse processing; an awareness
 +
 +
of the breadth of issues in the field; and
 +
 +
The ability to program (well!) in one or more of: C, C++, or Lisp.
 +
 +
 +
MRI offers excellent computational facilities and the opportunity to
 +
 +
work in an expanding team that carries out leading-edge research in
 +
 +
language technology. MRI is located on the campus of Macquarie
 +
 +
University in North Ryde, a suburb of Sydney, Australia, one of the
 +
 +
world's most beautiful cities.
 +
 +
 +
The positions will become available from January 1997, although actual
 +
 +
start dates are negotiable. The positions are open to those
 +
 +
considering postdoctoral positions as well as more experienced
 +
 +
candidates. Please send your application (including a CV and list of
 +
 +
publications) by email to Robert Dale (Robert.Dale(at)mq(dot)edu(dot)au) as soon
 +
 +
as possible and by January 1st 1997 at latest. Early indications of
 +
 +
interest would be useful if received by December 13th 1996. Informal
 +
 +
enquiries can be sent to the same address.
 +
 +
 +
Find out more about MRI at <http://www.mri.mq.edu.au/ltg/>
 +
 +
 +
 +
----
 +
 +
 +
Topic 6:
 +
 +
From: yarowsky(at)blaze(dot)cs(dot)jhu(dot)edu (David Yarowsky)
 +
 +
Subject: Call for Papers - EMNLP-2
 +
 +
 +
The Association for Computational Linguistics and its
 +
 +
Special Interest Group SIGDAT announce the
 +
 +
                      <center>  Second Conference on</center>
 +
 +
          <center>Empirical Methods in Natural Language Processing</center>
 +
 +
                            <center>(EMNLP-2) </center>
 +
 +
 +
                  <center> Preliminary Call For Papers </center>
 +
 +
 +
WHEN:    August 1-2, 1997 (Immediately following AAAI-97)
 +
 +
WHERE:    Brown University, Providence, Rhode Island, USA
 +
 +
 +
CONFERENCE DESCRIPTION:
 +
 +
In the spirit of SIGDAT events, this conference will offer a general
 +
 +
forum for novel research in corpus-based and statistical natural
 +
 +
language processing. Areas of interest include (but are not limited
 +
 +
to):
 +
 +
- robust parsing, phrase structure analysis
 +
 +
- part of speech tagging
 +
 +
- term and name identification
 +
 +
- word sense disambiguation
 +
 +
- morphological analysis
 +
 +
- anaphora resolution
 +
 +
- event categorization
 +
 +
- discourse structure identification
 +
 +
- alignment of parallel texts and bilingual terminology
 +
 +
- language modelling
 +
 +
- lexicography
 +
 +
- machine translation
 +
 +
- spelling and grammar correction
 +
 +
 +
SPECIAL SESSIONS: INFORMATION EXTRACTION and INFORMATION RETRIEVAL
 +
 +
 +
In addition, we encourage submissions that describe and evaluate the
 +
 +
strengths, weaknesses, and recent advances in corpus-based NLP as
 +
 +
applied to INFORMATION EXTRACTION and INFORMATION RETRIEVAL (IR).
 +
 +
 +
In recent years a number of corpus-based techniques for the automatic
 +
 +
linguistic annotation of text have been developed.  How well do these
 +
 +
techniques for lexical tagging, parsing, anaphora resolution, etc.,
 +
 +
handle the specific problems encountered in practical language
 +
 +
processing tasks like information extraction and information
 +
 +
retrieval?  When and how do current techniques fail?  What new methods
 +
 +
have been developed to address the deficiencies of existing algorithms
 +
 +
for these tasks or to address problems specific to information
 +
 +
extraction? What problems still lack an adequate empirical solution?
 +
 +
How can data-driven NLP methods be used to improve the performance of
 +
 +
IR systems?  Conversely, how can feedback from an IR system
 +
 +
effectively inform empirical techniques for natural language
 +
 +
understanding?
 +
 +
 +
PROGRAM CHAIRS:
 +
 +
{|
 +
  |  Claire Cardie      || Cornell University (chair)
 +
  |-
 +
  | Ralph Weischedel    ||BBN Systems and Technologies (co-chair)
 +
|}
 +
 +
 +
LOCAL ARRANGEMENTS:
 +
 +
{|
 +
  | Eugene Charniak      ||Brown University
 +
 +
|}
 +
 +
SPONSOR:  SIGDAT (ACL's special interest group for linguistic data and corpus-based approaches to NLP)
 +
 +
 +
FORMAT FOR SUBMISSION: Authors should submit a full-length paper
 +
 +
(3500-8000 words) either electronically or in hardcopy.  Electronic
 +
 +
submissions should be mailed to "cardie(at)cs(dot)cornell(dot)edu" and must
 +
 +
either be (a) plain ascii text, (b) a single postscript file (US
 +
 +
letter format), or (c) a LaTex file. In the latter case, please use
 +
 +
the aclsub style file and include only .EPS (encapsulated postscript)
 +
 +
figures. The aclsub style file is available at
 +
 +
http://www.cs.cornell.edu/Info/People/cardie/emnlp/aclsub.sty or via
 +
 +
ftp from ftp.cs.cornell.edu/pub/cardie/emnlp/aclsub.sty. Hardcopy
 +
 +
submissions should be mailed to Claire Cardie (address below), and
 +
 +
should include six (6) copies of the paper.
 +
 +
 +
REQUIREMENTS: Papers should describe original work. A paper accepted
 +
 +
for presentation cannot be presented or have been presented at any
 +
 +
other meeting. Papers submitted to other conferences will be
 +
 +
considered, as long as this fact is clearly indicated in the
 +
 +
submission.
 +
 +
SCHEDULE:
 +
 +
{|
 +
  |-
 +
  |Submission deadline:    || March 3, 1997
 +
  |-
 +
  |Notification date:      ||April 21, 1997
 +
  |-
 +
  |Camera-ready copy due:  ||June 10, 1997
 +
  |-
 +
  |Conference dates:        ||August 1-2, 1997
 +
|}
 +
 +
 +
CONTACTS:
 +
 +
{|
 +
  |-
 +
|Claire Cardie                          ||  Ralph Weischedel
 +
  |-
 +
|Cornell University   ||BBN Systems and Technologies
 +
  |-
 +
|Department of Computer Science            ||70 Fawcett Street
 +
  |-
 +
|4142 Upson Hall                          || Cambridge, MA 02138 
 +
  |-
 +
|Ithaca, NY 14850  USA                    || USA
 +
  |-
 +
|cardie(at)cs(dot)cornell(dot)edu          ||          weischedel(at)bbn(dot)com
 +
  |-
 +
|(607)255-9206                            ||(617)873-3496
 +
 +
|}
 +
 +
----
 +
 +
 +
Topic 7:
 +
From m.scordilis(at)wcl(dot)ee(dot)upatras(dot)gr Mon Dec 23 17:46:27 1996
 +
 +
Subject: EUROSPEECH'97 FINAL CALL FOR PAPERS
 +
 +
 +
<center> European Speech Communication Association</center>
 +
 +
<center>   (ESCA)</center>
 +
 +
 +
      <center> EUROSPEECH'97</center>
 +
 +
 +
<center> 5th EUROPEAN CONFERENCE20</center>
 +
 +
  <center> ON SPEECH COMMUNICATION AND TECHNOLOGY</center>
 +
 +
 +
    <center>  RHODES, GREECE</center>
 +
 +
  <center>  22-25 SEPTEMBER 1997</center>
 +
 +
 +
<center>  FINAL CALL FOR PAPERS</center>
 +
 +
 +
AIMS
 +
 +
The Fifth biennial European Conference on Speech Communication and Technology,
 +
 +
EUROSPEECH'97, of the European Speech Communication Association (ESCA), will be
 +
 +
held on the island of Rhodes, Greece, organized by the University of Patras,
 +
 +
Wire Communications Laboratory.  Rhodes is situated in the southern Aegean Sea,
 +
 +
in the Mediterranean and it is famous for its natural beauty, its archeological
 +
 +
treasures and its highly developed tourism. ESCA is the European organization
 +
 +
that promotes research, development and applications in SPEECH COMMUNICATION
 +
 +
AND TECHNOLOGY. Host cities of the previous conferences were Paris (1989),
 +
 +
Genova (1991), Berlin (1993) and Madrid (1995). The upcoming conference will
 +
 +
include the latest developments in this field of major international
 +
 +
importance, presented in oral and poster sessions .  Furthermore it will
 +
 +
include several keynote addresses by distinguished scientists. All
 +
 +
presentations and printed material will be in English, which is the official
 +
 +
language of the conference. In addition to the technical program, an exhibition
 +
 +
of products, services and prototypes related to Speech and Language
 +
 +
Communication and Technology will be held during the conference. Prospective
 +
 +
authors are invited to propose papers in any of the listed technical areas.
 +
 +
TECHNICAL AREAS
 +
 +
 +
A. Speech production and perception
 +
 +
B. Phonetics and phonology
 +
 +
C. Prosody
 +
 +
D. Neurophysiology, psychoacoustics and psycholinguistics of speech
 +
 +
E. Auditory modeling
 +
 +
F. Speech analysis and modeling
 +
 +
G. Neural networks for speech and language processing
 +
 +
H. Robust speech processing, signal enhancement and noise reduction
 +
 +
I. Text-to-speech synthesis
 +
 +
J. Speech and audio coding and transmission
 +
 +
K. Speech recognition and understanding
 +
 +
L. Language modeling
 +
 +
M. Spoken dialogue systems design
 +
 +
N. Speaker and language recognition
 +
 +
O. Spoken language resources, assessment, standards and human factors
 +
 +
P. Multimodal speech and language processing20
 +
 +
Q. Technology for speech and language acquisition and learning
 +
 +
R. Applications for speech, language and hearing disorders and aids for
 +
 +
the communication impaired
 +
 +
S. Speech and language engineering for the telecommunications
 +
 +
T. Systems, hardware and architectures for speech processing
 +
 +
U. Applications of speech technology
 +
 +
V. Other related areas or emerging techniques and applications
 +
 +
 +
SUBMISSION OF ABSTRACTS
 +
 +
Abstracts of original, not elsewhere published papers may be submitted either
 +
 +
by post (four copies must be submitted) or by e-mail in postcript or ascii
 +
 +
format only. They must be received no later than 1 February 1997 together with
 +
 +
the completed EUROSPEECH'97 Abstracts Cover Form given below. Abstracts should
 +
 +
not exceed two A4 pages (including figures and references). All submissions
 +
 +
will be acknowledged. E-mail abstracts will be acknowledged within 24 hours. If
 +
 +
they are not acknowledged, please check the e-mail address and resubmit. All
 +
 +
abstracts will be refereed by the Scientific Programme Committee. Submission of
 +
 +
an abstract implies a commitment to present the paper if accepted.
 +
 +
ABSTRACTS SUBMISSION ADDRESS:
 +
 +
EUROSPEECH'97
 +
 +
Wire Communications Laboratory
 +
 +
Department of Electrical and Computer Engineering
 +
 +
University of Patras
 +
 +
26110 Rion, Patras, GREECE
 +
 +
E-mail: Abstracts-EURO97(at)wcl(dot)ee(dot)upatras(dot)gr
 +
 +
 +
SPECIAL SESSIONS
 +
 +
 +
EUROSPEECH'97 will include a Special Session on "Education for Language &
 +
 +
Speech Communication Sciences", which aims to address educational issues of
 +
 +
Phonetics, Spoken Language Engineering, Speech and Language Therapy, Computer
 +
 +
assisted learning (CAL) and the use of internet.  Abstracts submitted for this
 +
 +
session must be indicated in the space provided in the Abstracts Cover
 +
 +
Form. For more information please contact:
 +
{|
 +
|Gerrit Bloothooft          || 20
 +
|}
 +
Research Institute for Language and Speech (OTS)
 +
 +
Trans 10, 3512 JK Utrecht, The Netherlands
 +
 +
Phone: +31.30.2536042
 +
 +
Fax:  +31.30.2536000
 +
 +
Email: Gerrit.Bloothooft(at)let(dot)ruu(dot)nl
 +
 +
 +
SCHEDULE
 +
 +
 +
{|
 +
|Submission of abstracts ||To be received by ||1 February 1997
 +
|-
 +
|Notification of acceptance ||To be mailed out by ||1 April 1997
 +
|-
 +
|Submission of photo-ready papers ||To be received by ||20 May 1997
 +
|}
 +
 +
 +
SATELLITE EVENTS
 +
 +
 +
ESCA WORKSHOP ON INTONATION, 18-20 September 1997, at Athens, Greece.
 +
 +
Information contact: Antonis Botinis
 +
 +
Tel: +30 1 7211119
 +
 +
Fax: +30 1 7228981
 +
 +
E-mail: tonesca(at)di(dot)uoa(dot)gr
 +
 +
WWW server: http://www.di.uoa.gr/esca
 +
 +
 +
EU SPEECH PROJECTS DAY, Monday, 22 September 1997, 9:00-13:00,
 +
 +
Convention Centre, Rodos Palace Hotel, Rhodes, Greece.
 +
 +
Information contact: Giovanni Battista Varile
 +
 +
European Commission, DG XIII E5 - Language Engineering
 +
 +
Tel: +352 430 132 867 Fax: +352 430 134 999
 +
E-mail: Giovanni.Varile(at)lux(dot)dg13(dot)cec(dot)be
 +
 +
 +
COCOSDA WORKSHOP'97 (The International Coordinating Committee for Speech
 +
 +
Databases and Speech I/O Systems Assessment), Friday, 26 September 1997,
 +
 +
9:00-13:00, Convention Centre, Rodos Palace Hotel.
 +
 +
Information contact: Mark Liberman
 +
 +
University of Pennsylvania
 +
 +
Tel: +1 215 898 0464 Fax:  +1 215 573 2175
 +
 +
E-mail:  myl(at)unagi(dot)cis(dot)upenn(dot)edu
 +
 +
 +
European Tutorial & Research Workshop on AUDIO-VISUAL SPEECH PROCESSING:
 +
 +
Computational & Cognitive Science Approaches, 27-28 September 1997,
 +
 +
Centre, Rodos Palace Hotel, Rhodes (Greece).
 +
 +
Information contact: Christian BENOIT
 +
 +
Institut de la Communication Parlee, UPRESA CNRS No 5009, Universite
 +
 +
Stendhal,20
 +
 +
BP 25 X, F38040 Grenoble Cedex 9, FRANCE
 +
 +
Tel: (+33).4.76.82.43.36 Fax: (+33).4.76.82.43.35
 +
 +
E-mail: benoit(at)icp(dot)grenet(dot)fr
 +
 +
Web page: http://ophale.icp.grenet.fr/
 +
 +
 +
COST WORKSHOP (Cooperation in the field of Scientific and Technical
 +
 +
research), 26-27 September 1997, Athens, Greece. Information contacts:
 +
 +
COST 249 COST 250
 +
 +
Continuous Speech Recognition Speaker Recognition in Telephony
 +
 +
{|
 +
|Jean Pierre Martens ||Andrea Paoloni
 +
|-
 +
|Tel: +32 91 264 3395 ||Tel: +39 6 5480 3351
 +
|-
 +
|Fax: +32 91 264 3594 ||Fax: +39 6 5480 4405
 +
|-
 +
|E-mail: martens(at)elis(dot)rug(dot)ac(dot)be ||E-mail: pao(at)fub(dot)it
 +
|}
 +
 +
 +
WEB-SITE
 +
 +
The Call for Papers, Call for Exhibitors and Sponsors, all necessary
 +
 +
forms, and continuously updated information about the Conference, as
 +
 +
well as about Greece and Rhodes, can be found at our web site at:
 +
 +
<http://www.cti.gr/~ee-www/>
 +
 +
 +
 +
----
 +
 +
 +
Topic 8:
 +
 +
From: Leo Joskowicz <josko(at)cs(dot)huji(dot)ac(dot)il>
 +
 +
Subject: BISFAI'97
 +
 +
 +
                <center> ******  Call for Papers  ****** </center>
 +
 +
                            <center> BISFAI '97 </center>
 +
 +
 +
                  <center>The Fifth Bar-Ilan Symposium on </center>
 +
 +
                <center>Foundations of Artificial Intelligence </center>
 +
 +
 +
                        <center>  June 16-18, 1997 </center>
 +
 +
              <center> Bar-Ilan University, Ramat-Gan, Israel </center>
 +
 +
 +
                      <center> in cooperation with </center>
 +
 +
 +
            <center> Israel Association for Artificial Intelligence </center>
 +
 +
      <center> Israeli Society for Theoretical Computer Science </center>
 +
 +
      <center> Gelbart Institute for Mathematical Sciences </center>
 +
 +
              <center>  The Association for Mathematics of Language </center>
 +
 +
    <center> The Leibniz Center for Research in Computer Science </center>
 +
 +
 +
The focus of BISFAI '97 will be on Intelligent Agents.  The Symposium will,
 +
 +
however, retain its broad scope, and welcomes high quality research papers
 +
 +
in various areas of Artificial Intelligence, including machine learning,
 +
 +
automated reasoning, knowledge representation, neural nets, natural
 +
 +
language processing, etc.
 +
 +
 +
The concept of an agent has become important in both artificial
 +
 +
intelligence and mainstream computer science. An agent is a hardware or
 +
 +
software system that is automonous, interactive with and reactive to its
 +
 +
environment and other agents. An agent can also be pro-active in taking the
 +
 +
initiative in goal-directed behaviour.
 +
 +
 +
We solicit papers in all areas of Artificial Intelligence, and in
 +
 +
particular in the area of Intelligent Agents.  Agents have a clear and
 +
 +
growing importance, both practical and theoretical.  Because of their
 +
 +
commercial relevance, we encourage practitioners from industry to submit
 +
 +
papers dealing with various practical aspects.
 +
 +
 +
Distinguished Invited Speakers (tentative):
 +
 +
{|
 +
|C. Boutilier ||(U. of British Columbia)
 +
|-
 +
|V. Lesser  ||(U. of Massachusetts)
 +
|-
 +
|J. Rosenschein  ||(Hebrew U.)
 +
|-
 +
|G. Shafer ||(Rutgers U.)
 +
|-
 +
|Y. Shoham      || (Stanford U.)
 +
|-
 +
|P. Struss ||(Technical University of Munich)
 +
|-
 +
|W. Wahlster    || (DFKI GmbH)
 +
|}
 +
 +
 +
THE 1997 ISRAELI FEDERATED COMPUTING CONFERENCE: The Symposium will be part
 +
 +
of the new Israeli Federated Computing Conference (IFCC).  For contact
 +
 +
points on this conference, see below).  The IFCC will also include the
 +
 +
Eighth Israeli Conference on Computer-Based Systems and Software
 +
 +
Engineering (CBSE), which will take place on June 18-19, 1997, and the
 +
 +
Fifth Israeli Symposium on Theory of Computing and Systems (ISTCS'97),
 +
 +
which will take place on June 17-19, 1997.
 +
 +
 +
Paper Submission: Submit three hard copies of an extended abstract (4-10
 +
 +
pages), or full paper, by February 2nd 1997, to
 +
 +
Leo Joskowicz
 +
 +
Institute of Computer Science
 +
 +
The Hebrew University of Jerusalem
 +
 +
Givat Ram, Jerusalem 91904, Israel
 +
 +
E-mail: josko(at)cs(dot)huji(dot)ac(dot)il
 +
 +
 +
Authors will be notified of acceptance by 20th March 1997. A final version
 +
 +
of the accepted will appear in the conference preprints, which will be
 +
 +
distributed to participants at the symposium.  Selected refereed full
 +
 +
length papers will be published in a special issue of the Annals of
 +
 +
Mathematics and Artificial Intelligence as a permanent record of the
 +
 +
Symposium.  These should be submitted shortly after the conclusion of the
 +
 +
Symposium.
 +
 +
 +
Information on registration, accommodations, etc., will appear in future
 +
 +
announcements, or contact: bisfai(at)cs(dot)biu(dot)ac(dot)il.
 +
 +
The web page site is:
 +
 +
<http://www.cs.biu.ac.il:8080/~schwart/bisfai97.html>
 +
 +
 +
{|
 +
  |  Symposium Chair
 +
|-
 +
|S. Kraus        ||(Bar-Ilan U.)
 +
|-
 +
|  Program Co-Chairs
 +
|-
 +
|D. Lehmann || (Hebrew U.)
 +
|-
 +
|L. Joskowicz ||(Hebrew U.)
 +
|}
 +
 +
 +
----
 +
 +
 +
eof
 +
----
 +
 +
==1996==
 +
===Issue 7===
 +
<u>Date: 19 Nov 1996</u>
 +
 +
----
 +
 +
TOPICS:
 +
 +
1. CFP AI-ED 97 Kobe, Japan. Deadline January 23rd 1997 (partial)
 +
 +
2. Call for Participation KBCS - Bombay, India. Dec 16-18 1996 (partial)
 +
 +
3. Subject: UM97 CFP - Deadline Nov 25 1996 (full)
 +
----
 +
 +
 +
 +
----
 +
 +
Topic 1:
 +
 +
From: miz(at)ei(dot)sanken(dot)osaka-u(dot)ac(dot)jp (Riichiro MIZOGUCHI)
 +
 +
Subject: CFP AI-ED 97 Kobe, Japan. Deadline January 23rd 1997
 +
 +
NOTE: Full call for paper on the Web.
 +
 +
 +
CALL FOR PAPERS
 +
 +
A I - E D  9 7
 +
 +
8TH WORLD CONFERENCE ON ARTIFICIAL INTELLIGENCE IN EDUCATION
 +
 +
---  Knowledge and Media in Learning Systems  ---
 +
 +
 +
19th - 22nd August, 1997
 +
 +
Kobe International Conference Center, JAPAN
 +
 +
URL: http://www.ei.sanken.osaka-u.ac.jp/aied97/cfp.html
 +
 +
 +
Co-Sponsored by:
 +
 +
Artificial Intelligence in Education Society(AI-ED) and
 +
 +
Japanese Society for Information and Systems in Education(JSISE)
 +
 +
 +
In Cooperation with:
 +
 +
Asia-Pacific Chapter of the AACE
 +
 +
Japanese Association for Artificial Intelligence
 +
 +
 +
The 8th World Conference on Artificial Intelligence in Education
 +
 +
(AI-ED 97) is one of a series of international conferences designed to
 +
 +
report the best research in the field of AI in Education and to
 +
 +
provide opportunities for the cross-fertilisation of information and
 +
 +
ideas on research and applications in this field.
 +
 +
 +
The theme for 1997 will be Knowledge and Media in Learning Systems,
 +
 +
and papers that explore the emerging roles of intelligent multimedia
 +
 +
and distributed technologies as well as computer supported
 +
 +
collaboration within that theme will be particularly welcome.
 +
 +
 +
You are invited to submit proposals for research papers, survey papers,
 +
 +
themed papers, posters, tutorials, workshops, and panels.
 +
 +
All proposals will be reviewed for inclusion in the technical program.
 +
 +
 +
Scope
 +
 +
 +
The technical program focuses on research activities linking
 +
 +
Artificial Intelligence theories and techniques with Educational
 +
 +
theory and practice. Areas of interest include but are not limited to:
 +
 +
 +
Agents
 +
 +
Architectures
 +
 +
Authoring systems and tutoring shells
 +
 +
Case-based systems
 +
 +
Cognitive development
 +
 +
Cognitive diagnosis
 +
 +
Collaboration and collaborative tools
 +
 +
Computer-assisted language learning
 +
 +
Conceptual change
 +
 +
Educational robotics
 +
 +
Evaluation of instructional systems
 +
 +
Human factors and interface design
 +
 +
Intelligent multimedia and hypermedia systems
 +
 +
Intelligent tutoring systems
 +
 +
Knowledge and skill acquisition
 +
 +
Knowledge representation for instruction
 +
 +
Learning environments and microworlds
 +
 +
Modelling pedagogical interactions
 +
 +
Motivation
 +
 +
Natural language interfaces
 +
 +
Networked learning and teaching systems
 +
 +
Non-standard and innovative interfaces
 +
 +
Principles and tools for instructional design
 +
 +
Social and cultural aspects of learning
 +
 +
Student modelling
 +
 +
Higher-order thinking skills and metacognition
 +
 +
Theories of teaching
 +
 +
Visual and graphical interfaces
 +
 +
 +
+In addition to RESEARCH papers and posters in the above areas, SURVEY
 +
 +
papers will also be accepted. A survey paper will offer a coherent and
 +
 +
critical summary of achievements and outstanding problems in an area.
 +
 +
 +
+To provoke debate and reflection, THEME papers are also sought under
 +
 +
the specific title "Knowledge and Media in Learning Systems - the next
 +
 +
15 years".
 +
 +
 +
+Exhibits are expected to be an integral part of the AI-ED 97
 +
 +
conference. Companies or institutions offering to exhibit AI-ED
 +
 +
products are invited.
 +
 +
 +
 +
----
 +
 +
Topic 2:
 +
 +
From: KBCS Word Processing <kbcs(at)cs(dot)uni-sb(dot)de
 +
 +
<center><u>IMPORTANT DATES </u></center>
 +
 +
PAPERS AND POSTERS
 +
{|
 +
| Monday,                || Receipt by e-mail of abstracts and
 +
  |-
 +
|25 November 1996      || author information
 +
  |-
 +
|
 +
  |-
 +
| Monday,                || Receipt of electronic submissions
 +
    |-
 +
|2 December 1996        || (optional)
 +
  |-
 +
|
 +
    |-
 +
|Tuesday,              || E-mail notification to authors if the
 +
    |-
 +
|3 December 1996        ||requirement of hard-copy submission is waived
 +
  |-
 +
|
 +
    |-
 +
|Friday,                || Receipt of 5 hard copies of each
 +
    |-
 +
|6 December 1996        || manuscript (except where the hard-copy requirement was waived on 3 December)
 +
  |-
 +
|
 +
    |-
 +
|Wednesday,              ||Notification of authors by e-mail about
 +
    |-
 +
|26 February 1997        ||acceptance or rejection of submissions
 +
  |-
 +
|
 +
    |-
 +
|Monday,                || Receipt of electronic versions of
 +
    |-
 +
|31 March 1997          || camera-ready papers and summaries of posters
 +
|}
 +
 +
 +
DOCTORAL CONSORTIUM
 +
 +
{|
 +
  |Wednesday,              ||Receipt by e-mail of 3-page submissions
 +
    |-
 +
|5 February 1997        ||as ASCII text
 +
  |-
 +
|
 +
    |-
 +
|Wednesday,              ||Notification to authors by e-mail about
 +
  |-
 +
| 5 March 1997            ||acceptance or rejection of submissions
 +
  |-
 +
|
 +
    |-
 +
|Monday,                ||Receipt of electronic versions of
 +
    |-
 +
|31 March 1997          ||camera-ready summaries of presentations
 +
|}
 +
 +
 +
WORKSHOPS
 +
 +
 +
{|
 +
  |Monday,                || Receipt by e-mail of 3-page workshop
 +
  |-
 +
| 20 January 1997        ||proposals as ASCII text
 +
  |-
 +
|
 +
  |-
 +
| Friday,                || Notification by e-mail to workshop
 +
    |-
 +
|14 February 1997      || proposers about acceptance or rejection of proposals
 +
  |-
 +
|
 +
  |Friday,                ||Submission, by proposers of accepted
 +
  |-
 +
| 21 February 1997        ||workshops, of final calls for participation
 +
  |-
 +
|
 +
    |-
 +
|Tuesday,                ||Availability via the UM97 Web site
 +
  |-
 +
| 25 February 1997      || and by e-mail of calls for participation in workshops
 +
|}
 +
 +
 +
SYSTEM DEMONSTRATIONS
 +
 +
 +
{|
 +
  |Tuesday,              || Registration of system demonstrations
 +
    |-
 +
|15 April 1997          ||by e-mail
 +
|}
 +
 +
------------------------------------------------------------------
 +
 +
 +
 +
                <center> REASONS TO SUBMIT TO UM97</center>
 +
 +
 +
As a potential author, you may now be wondering whether to
 +
 +
write up your work for UM97 or for a journal or another conference.
 +
 +
Here are some points to bear in mind:
 +
 +
 +
1. A paper that appears in the proceedings will have the status of a
 +
 +
peer-reviewed publication in an internationally distributed
 +
 +
edited volume, which will be published by SpringerWien-New York.
 +
 +
2. As an additional means of ensuring accessibility of the
 +
 +
proceedings, electronic versions of the papers will remain
 +
 +
available on the World Wide Web site of User Modeling, Inc.
 +
 +
for a long time after the conference.
 +
 +
3. Publication in the proceedings volume can be viewed as a
 +
 +
step along the way to the production of a major journal article
 +
 +
about your research.  The deadline will encourage you to produce
 +
 +
an initial version; the comments of the members of the international
 +
 +
program committee will help you to improve it; and the feedback
 +
 +
that you get on the final conference paper will help you to
 +
 +
produce a strong full journal manuscript. Journal editors will
 +
 +
not in general be bothered by the fact that a related
 +
 +
conference-length paper has been published, as long as your
 +
 +
journal submission is sufficiently longer, more detailed, and
 +
 +
otherwise expanded relative to the conference paper. (The journal
 +
 +
"User Modeling and User-Adapted Interaction" is already reserving
 +
 +
space for articles of this sort.)
 +
 
 +
4. Experience with previous conferences in the UM series has
 +
 +
shown that they provide an exceptionally good environment for
 +
 +
exchanging ideas and making new contacts. There is a sharp
 +
 +
contrast with broader conferences, at which it is often hard to
 +
 +
find someone who is interested in the same topics as you are.
 +
 +
5. Finally, people who have visited Sardinia often claim that
 +
 +
it is one of the most beautiful places the world. There is
 +
 +
nothing wrong with enjoying this beauty for a few days before or
 +
 +
after UM97.
 +
 +
 +
----
 +
 +
eof
 +
----
 +
===Issue 6===
 +
<u>Date: 20 Oct 1996</u>
 +
 +
----

 +
TOPICS:
 +
 +
1. E W N L G - 9 7 6th European Workshop on Natural Language Generation
 +
<p style=“"text-indent:1em”>DEADLINE NOV 15 1996!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!</p>
 +
2. Post in Computational Linguistics, Stirling <jld1(at)stir(dot)ac(dot)uk>
 +
 +
3. Practical Human-computer conversation 1997 <yorick(at)dcs(dot)shef(dot)ac(dot)uk>
 +
----

 +
 +
----

 +
Topic 1:
 +
 +
From: he232ho(at)rs1-hrz(dot)uni-duisburg(dot)de (Wolfgang Hoeppner)
 +
 +
Subject: EWNLG-97
 +
 +
-----
 +
CALL FOR PAPERS
 +
 +
 +
E W N L G - 9 7
 +
 +
 +
6th European Workshop on
 +
 +
Natural Language Generation
 +
 +
 +
March 24 - 26, 1997
 +
 +
 +
Gerhard-Mercator University, Duisburg, Germany
 +
 +
 +
The workshop aims to bring together researchers interested in Natural
 +
 +
Language Generation from such different perspectives as Linguistics,
 +
 +
Artificial Intelligence, Psychology, Cognitive Science, and Engineering.
 +
 +
The meeting continues the tradition of a series of workshops held
 +
 +
biannually in Europe (Royaumont, 1987; Edinburgh, 1989; Judenstein,
 +
 +
1991; Pisa, 1993; and Leiden, 1995) but it is open to researchers from
 +
 +
all over the world.
 +
 +
 +
Program Committee:
 +
 +
Stephan Busemann, Saarbruecken
 +
 +
Alison Cawsey, Edinburgh
 +
       
 +
Robert Dale, Sydney
 +
       
 +
Wolfgang Hoeppner, Duisburg (chair)
 +
       
 +
Richard Kittredge, Montreal
 +
       
 +
Stephan Mehl, Duisburg
 +
       
 +
Koenrad deSmedt, Bergen
 +
       
 +
Michael Zock, Paris
 +
 +
 +
Papers, posters and demonstrations are invited on original and
 +
 +
substantial work related to the automatic generation of natural
 +
 +
language, including computational linguistics research, artificial
 +
 +
intelligence methods, computer models of human language processing,
 +
 +
empirical research, and the development and evaluation of applied
 +
 +
systems. Contributions on all aspects of natural language generation are
 +
 +
welcome, but the special theme of this workshop will be
 +
 +
'System Architectures for Text Generation'.
 +
 +
 +
This topic comprises a variety of more specific questions, e.g. planning
 +
 +
and/or schemata, pragmatic impact on content selection and form
 +
 +
determination, serial or incremental processing, macro-planning and
 +
 +
micro-planning.
 +
 +
 +
To encourage a workshop atmosphere while allowing a relatively large
 +
 +
number of people to participate, selected papers will be given large time
 +
 +
slots including ample discussion time; other papers will be grouped for
 +
 +
shorter presentations and mutual interaction, and there will be sessions
 +
 +
for posters and computer demonstrations.
 +
 +
 +
Submissions:
 +
 +
 +
Researchers wishing to present a PAPER are requested to submit three
 +
 +
copies of an original unpublished article (10 pages). To allow for
 +
 +
anonymous reviewing the name(s) and complete adress(es) of the
 +
 +
author(s) have to be provided on a separate sheet. We would appreciate
 +
 +
that you additionally send an electronic version of the paper (email or
 +
 +
diskette).
 +
 +
 +
Researchers wishing to present a POSTER are invited to submit three
 +
 +
copies of a reduced version of their poster on 4 normal pages that
 +
 +
together form an A2 size sheet. Use a normal character size. As with
 +
 +
papers any personal information about the author(s) should appear on a
 +
 +
separate sheet.
 +
 +
 +
Researchers wishing to demonstrate a computer PROGRAM are invited to
 +
 +
send three copies of a short description of their program together with
 +
 +
some examples of input and output and hardware requirements. Please
 +
 +
include the name(s) and complete address(es) of the author(s) in the
 +
 +
description.
 +
 +
            <center>  ********** N E W  D E A D L I N E *************</center>
 +
 +
All contributions must be sent BEFORE NOVEMBER 15, 1996 to the
 +
 +
Program Chairman at the following address:
 +
 +
 +
Prof. Dr. Wolfgang Hoeppner
 +
       
 +
Gerhard-Mercator University, Duisburg
 +
       
 +
FB3 * Computational Linguistics
 +
       
 +
D-47048 Duisburg, Germany
 +
 +
   
 +
Tel.: +49 203 379-2006/2008
 +
 +
email: hoeppner(at)unidui(dot)uni-duisburg(dot)de
 +
 +
 +
Internet: http://verdi.uni-duisburg.de/EWNLG-96.html
 +
 +
 +
Authors will be notified about acceptance or rejection by January 17, 1997.
 +
 +
 +
Local arrangements:
 +
 +
 +
Local arrangements are handled by: Wolfgang Hoeppner and Stephan
 +
 +
Mehl (University of Duisburg).
 +
 +
 +
The meeting will be held from the morning of Monday March 24, 1997
 +
 +
through afternoon on Wednesday 26, in 'Die Wolfsburg' situated in the
 +
 +
municipal forest of Duisburg. This conference site congresses and
 +
 +
workshops from all scientific areas and is equipped with excellent
 +
 +
presentation facilities and modern guest rooms.
 +
 +
 +
The cost of the workshop to each participant is currently estimated at
 +
 +
about DM 500 including accommodation and meals, but the participants'
 +
 +
fee may turn out to be lower depending on funding. The workshop will
 +
 +
also be open to a limited number of participants not contributing a
 +
 +
paper, poster or demo. A call for participation including more
 +
 +
information and a registration form will be sent out later as soon as the
 +
 +
program has been put together.
 +
 +
 +
Please direct any inquiries to the adress above.
 +
 +
<p>---------->------->----->--->->>> <<<-<---<-----<-------<----------</p>
 +
 +
 +
Prof. Dr. Wolfgang Hoeppner                              *********
 +
 +
Gerhard-Mercator-Universitaet Duisburg                *======*
 +
 +
Fachbereich 3 * Computerlinguistik                            *====*
 +
 +
D-47048 Duisburg                                                      *==*
 +
-----------------                                                          *
 +
 +
Tel.: (0203) 379-2006/2008
 +
 +
email: hoeppner(at)unidui(dot)uni-duisburg(dot)de
 +
 +
internet: http://verdi.uni-duisburg.de/hoeppner.html
 +
 +
or: http://verdi.uni-duisburg.de/Englisch/hoeppner.html
 +
<p>---------->------->----->--->->>> <<<-<---<-----<-------<----------</p>
 +
 +
----

 +
Topic 2:
 +
 +
From: Dr Judy L Delin <jld1(at)stir(dot)ac(dot)uk>
 +
 +
Subject: Post in Computational Linguistics, Stirling
 +
 +
 +
 +
Lectureship in Computational and Descriptive Linguistics
 +
 +
University of Stirling, Scotland
 +
 +
 +
The University wishes to expand its growing activity in descriptive and
 +
 +
computational linguistics by appointing a Lecturer to work alongside Dr.
 +
 +
Judy Delin in the Department of English Studies. 
 +
 +
 +
We are looking for an established researcher in the field who will invest in
 +
 +
the development of research and teaching at Stirling, with expertise in
 +
 +
discourse, pragmatics, contrastive text analysis, natural language
 +
 +
generation, and/or speech generation.  Experience or an interest in
 +
 +
contrastive text analysis in languages other than English, especially
 +
 +
Japanese, would be particularly desirable. The level of the appointment
 +
 +
reflects our expectation that the new person will be able to generate
 +
 +
external research funds and will have initiative in developing
 +
 +
collaborative research within and outside the group. The post will be
 +
 +
research-led, but the ideal candidate would also be able to help develop
 +
 +
future undergraduate and postgraduate teaching modules in linguistics
 +
 +
and computational linguistics. Future teaching and our research
 +
 +
development will also require expertise in programming for NLP.
 +
 +
 +
 +
Stirling is a small University situated in what is perhaps the most
 +
 +
beautiful campus in the U.K., and within easy reach of Edinburgh and
 +
 +
Glasgow.  The accommodation is modern and well-equipped (networked,
 +
 +
Unix workstation or other platform if preferred). The Lecturer will be part
 +
 +
of the Language and Communication Research Group, an interdisciplinary
 +
 +
group that includes researchers from Psychology,  Education, English
 +
 +
Studies, Japanese Studies, and the Centre for English Language
 +
 +
Teaching. Initiative in establishing further cross-disciplinary links will be
 +
 +
particularly encouraged.
 +
 +
 +
The post would be for two years in the first instance with good prospects of
 +
 +
renewal. The appointment will be on the Lecturer B Scale,  L. 20677 to
 +
 +
L. 26430 a year, with placement according to qualifications, experience,
 +
 +
and potential.  Starting date is negotiable, although we hope that the new
 +
 +
Lecturer will be with us by January 1997. 
 +
 +
 +
Informal enquiries are welcome: please contact Dr Judy Delin on(+44) (0)
 +
 +
1786 467974, email: jld1(at)stir(dot)ac(dot)uk, or consult the Web page at
 +
 +
http://www.stir.ac.uk/english/Communication/post.html. Anyone sending
 +
 +
email or making an enquiry will be informed of the official closing date,
 +
 +
which is likely to be during September 1996, and will be sent a copy of
 +
 +
the further particulars for the post once this date is finalised with
 +
 +
our Staff Office.
 +
 +
 +
 +
Dr Judy Delin
 +
 +
Department of English Studies/Language and Communication Research Group
 +
 +
University of Stirling
 +
 +
Stirling FK9 4LA
 +
 +
Scotland
 +
 +
 +
Tel: (+44) (0) 1786 467974
 +
 +
Fax: (+44) (0) 1786 466201
 +
 +
email: jld1(at)stir(dot)ac(dot)uk
 +
 +
URL:  http://www.stir.ac.uk/english/Communication/post.html
 +
 +
 +
----

 +
Topic 3:
 +
 +
From: Yorick Wilks <yorick(at)dcs(dot)shef(dot)ac(dot)uk>
 +
 +
Subject: Practical Human-computer conversation by Lake Como 1997
 +
 +
 +
CALL FOR EXPRESSIONS OF INTEREST: PLEASE RECIRCULATE THIS WIDELY
 +
 +
 +
1st INTERNATIONAL WORKSHOP ON HUMAN-COMPUTER CONVERSATION
 +
 +
 +
Bellagio, Italy, 14-16 July, 1997
 +
 +
We are seeking expressions of interest before formally
 +
 +
announcing a rather different kind of workshop: one that
 +
 +
will survey and demonstrate techniques for practical,
 +
 +
plausible, human computer conversation. The workshop would
 +
 +
be in the spirit of the Loebner Competition meetings, but
 +
 +
would not constitute any kind of "Turing" competition
 +
 +
under controlled deception conditions, but would, we hope,
 +
 +
give opportunity for extensive demonstrations of
 +
 +
working conversational systems, preferably without domain
 +
 +
restrictions.
 +
 +
 +
As well as practical demonstrations we would hope for papers
 +
 +
and discussions on How-To-Do-It: including abstract
 +
 +
discussions of the computer individual as well as reports of
 +
 +
practical experiences of using the large resources and knowledge data
 +
 +
bases now available through forms of information retrieval
 +
 +
and natural language processing and their impact (together
 +
 +
with fast access techniques) on high-quality conversation
 +
 +
simulations. The meeting is not intended to be yet another
 +
 +
get together on linguistic methods for dialogue modelling
 +
 +
or human-computer interaction, but rather based on the
 +
 +
assumption that, in a range of places, great strides are
 +
 +
actually being made in real conversation simulations from
 +
 +
practical techniques and points of view, and that all would
 +
 +
benefit from face-to-face interaction on this, as well as
 +
 +
exploring the industrial/commercial applications of these
 +
 +
technologies in HCI/WWW environments in the very near
 +
 +
future.
 +
 +
 +
The proposed site is the Grand Hotel Villa Serbelloni,
 +
 +
in Bellagio, Italy, on Lake Como, the
 +
 +
legendary site of Pliny's villa where the two arms of the
 +
 +
lake meet, and one of the most beautiful spots in the world,
 +
 +
though easily reached from Milan. The date, 14-16 July 1997,
 +
 +
immediately follows the EACL/ACL in Madrid.
 +
 +
Working system demonstrations
 +
 +
would be central, and there would also be a range of panels
 +
 +
on aspects of the state of the art.
 +
 +
 +
Interest is solicited by email at the address below from anyone
 +
 +
with new ideas, results or ongoing work to report on any aspect of
 +
 +
human-computer conversation, or those with an interest in or commitment
 +
 +
to the exploitation of this technology.
 +
 +
The emphasis should be on the software techniques for
 +
 +
communication in natural language and NOT on speech recognition
 +
 +
or speech synthesis.  Given sufficient interest
 +
 +
a committee will be established and conditions for submission
 +
 +
announced before the end of November 1996. Please put
 +
 +
Serbelloni in the message line of your email. Updatings of
 +
 +
developments for this workshop will be posted to:
 +
 +
http://www.dcs.shef.ac.uk/research/ilash/Meetings/Bellagio/
 +
 +
<p>*********************************</p>
 +
 +
Professor Yorick Wilks
 +
 +
AI and NN Research Group,
 +
 +
Department of Computer Science
 +
 +
University of Sheffield
 +
 +
Regent Court
 +
 +
211 Portobello St.,
 +
 +
Sheffield S1 4DP
 +
 +
UK
 +
 +
 +
phone: (44) 114 282 5561
 +
 +
fax:  (44) 114 278 0972
 +
 +
email: yorick(at)dcs(dot)shef(dot)ac(dot)uk
 +
 +
www:  http://www.dcs.shef.ac.uk/People/Y.Wilks
 +
<p>*********************************</p>
 +
 +
 +
 +
----

 +
eof
 +
----

 +
===Issue 5===
 +
Date: 07 Jul 1996
 +
<p>————————</p>
 +
 +
<p>======================================================================</p>
 +
TOPICS:
 +
 +
1. User Modeling Conference 1st CFP - <Cecile.Paris@itri(dot)brighton(dot)ac(dot)uk>
 +
 +
2. Generation thesis available - Lexical Semantics and Knowledge
 +
<p style=“text-indent:1em”>Representation in Multilingual Sentence Generation - <stede@cs(dot)tu-berlin(dot)de></p>
 +
3. Call for Participants - TALC96 - TEACHING AND LANGUAGE CORPORA
 +
<p style=“text-indent:1em”>Lancaster University, UK, 9th-12th August, 1996 - <spb@comp(dot)lancs(dot)ac(dot)uk></p>
 +
 +
4. 2nd CFP - International Conference on Knowledge Based Computer Systems
 +
<p style=“text-indent:1em”>Bombay, India - December 16-18, 1996 - Deadline Aug 15, 1996 -
 +
  <kbcs@konark(dot)ncst(dot)ernet(dot)in></p>
 +
 +
<p>======================================================================</p>
 +
Topic 1:
 +
 +
Subject: UM97: FIRST CALL FOR PAPERS
 +
 +
Date:    June 2-5 1997 - Deadline 25 November 1996
 +
 +
From:    Cecile Paris <Cecile.Paris@itri(dot)brighton(dot)ac(dot)uk>
 +
 +
 +
<center>UM97</center>
 +
 +
 +
<center> SIXTH INTERNATIONAL CONFERENCE ON USER MODELING</center>
 +
 +
<center>Chia Laguna, Sardinia, Italy, June 2-5 1997</center>
 +
 +
 +
                  <center>http://www.cs.uni-sb.de/UM97/ or</center>
 +
               
 +
      <center> http://www.crs4.it/UM97/</center>
 +
 +
-----------------------------------------------------------------
 +
 +
 +
Contents:
 +
 +
Background
 +
 +
Conference Topics
 +
 +
Conference Organization
 +
 +
Brief Submission Instructions
 +
 +
Contact Addresses
 +
 +
Important Dates
 +
 +
 +
<p>————————————— BACKGROUND ——————————————</p>
 +
 +
User modeling has been found to enhance the effectiveness
 +
 +
and/or usability of software systems in a wide variety of
 +
 +
situations. A user model is an explicit representation of
 +
 +
properties of a particular user. A system that constructs and
 +
 +
consults user models can adapt diverse aspects of its performance
 +
 +
to individual users.
 +
 +
 +
Techniques for user modeling have been developed and evaluated
 +
 +
by researchers in a number of fields, including artificial
 +
 +
intelligence, education, psychology, linguistics, human-computer
 +
 +
interaction, and information science.
 +
 +
 +
The International Conferences on User Modeling provide a forum
 +
 +
in which academic and industrial researchers from all of these
 +
 +
fields can exchange their complementary insights on user modeling
 +
 +
issues.  The size and format of the meetings support intensive
 +
 +
discussion, which often continues long after the conference has
 +
 +
ended.
 +
 +
 +
UM97 follows the Fourth and Fifth International Conferences on
 +
 +
User Modeling, which took place in Cape Cod, Massachusetts, in
 +
 +
August 1994 and Kailua-Kona, Hawaii in January 1996,
 +
 +
respectively.  UM97 will include tutorials, invited talks, paper
 +
 +
and poster sessions, a doctoral consortium, workshops, and system
 +
 +
demonstrations.
 +
 +
 +
Accepted papers, as well as summaries of other conference
 +
 +
contributions, will be published in a proceedings volume.
 +
 +
Information about the form of this publication will be made
 +
 +
available via the conference World Wide Web site. The Web site
 +
 +
will also provide access to electronic versions of contributions
 +
 +
to the conference.
 +
 +
 +
The journal "User Modeling and User-Adapted Interaction" is
 +
 +
reserving space for expanded versions of the best papers of UM97.
 +
 +
A $500 Best Paper Award is being sponsored by Kluwer Academic
 +
 +
Publishers.
 +
 +
 +
UM97 is being sponsored by AI*IA, the Italian Association for
 +
 +
Artificial Intelligence.
 +
 +
<p>——————————— CONFERENCE TOPICS ————————————</p>
 +
 +
The following nonexhaustive list gives some examples of topics
 +
 +
that are relevant to UM97:
 +
 +
 +
Construction of models of users' ...
 +
 +
 +
<p style="text-indent:1em">* knowledge, beliefs, and misconceptions,</p>
 +
<p style="text-indent:1em">* preferences,</p>
 +
<p style="text-indent:1em">* goals and plans,</p>
 +
<p style="text-indent:1em">* typical behaviors,</p>
 +
<p style="text-indent:1em"> * cognitive styles, ....</p>
 +
 +
 +
Exploitation of user models to achieve ...
 +
 +
 +
<p style="text-indent:1em">* adaptive information filtering and retrieval,</p>
 +
<p style="text-indent:1em">* tailored information presentation,</p>
 +
<p style="text-indent:1em">* transfer of task performance from user to system,</p>
 +
<p style="text-indent:1em">* selection of instructional interventions,</p>
 +
<p style="text-indent:1em">* interface adaptation, ....</p>
 +
 +
 +
Inference techniques involving ...
 +
 +
 +
<p style="text-indent:1em">* neural networks,</p>
 +
<p style="text-indent:1em">* psychometric methods,</p>
 +
<p style="text-indent:1em">* numerical uncertainty management,</p>
 +
<p style="text-indent:1em">* epistemic logic or other logic-based formalisms,</p>
 +
<p style="text-indent:1em">* default reasoning and truth maintenance,</p>
 +
<p style="text-indent:1em">* stereotype hierarchies, ....</p>
 +
 +
 +
Practical issues of ...
 +
 +
 +
<p style="text-indent:1em">* privacy and user model inspectability,</p>
 +
<p style="text-indent:1em">* user model consistency,</p>
 +
<p style="text-indent:1em">* empirical evaluation,</p>
 +
<p style="text-indent:1em">* standardization of user modeling shell systems, ....</p>
 +
 +
 +
Systems for adaptive ...
 +
 +
 +
<p style="text-indent:1em">* tutoring and provision of learning environments,</p>
 +
<p style="text-indent:1em">* explanation of system actions,</p>
 +
<p style="text-indent:1em">* on-line aiding,</p>
 +
<p style="text-indent:1em">* hypermedia and multimodal interaction,</p>
 +
<p style="text-indent:1em">* knowledge-based presentation design,</p>
 +
<p style="text-indent:1em">* product presentation,</p>
 +
<p style="text-indent:1em">* information management on the Internet,</p>
 +
<p style="text-indent:1em">* support of end-user programming,</p>
 +
<p style="text-indent:1em">* accommodation of users with special needs,</p>
 +
<p style="text-indent:1em">* support of collaboration, ....</p>
 +
 +
<p>—————————— CONFERENCE ORGANIZATION ——————————</p>
 +
 +
{|
 +
|General Chair:
 +
|-
 +
| Carlo Tasso          || University of Udine, Italy
 +
|-
 +
|
 +
|-
 +
|Organizing Chair:
 +
  |-
 +
|Alessandro Micarelli  ||University of Rome 3, Italy
 +
|-
 +
|
 +
|-
 +
|Program Co-Chairs:
 +
|-
 +
|Anthony Jameson      ||University of Saarbruecken, Germany
 +
|-
 +
|Cecile Paris        || University of Brighton, UK
 +
|-
 +
|
 +
|-
 +
|Program Committee:
 +
|-
 +
|Nicholas J. Belkin    ||Rutgers University, USA
 +
|-
 +
|Beatrice Cahour      || CNRS Rouen, France
 +
|-
 +
|Sandra Carberry      ||University of Delaware, USA
 +
|-
 +
|Albert Corbett        ||Carnegie Mellon University, USA
 +
|-
 +
|Fiorella de Rosis    ||University of Bari, Italy
 +
|-
 +
|Oren Etzioni          ||University of Washington, USA
 +
|-
 +
|Gerhard Fischer      ||University of Colorado, Boulder, USA
 +
|-
 +
|Helen M. Gigley      ||Office of Naval Research, USA
 +
|-
 +
|Brad Goodman          ||The MITRE Corporation, USA
 +
|-
 +
|Eric Horvitz          ||Microsoft Research, USA
 +
|-
 +
|Judy Kay              ||Sydney University, Australia
 +
|-
 +
|Alfred Kobsa          ||GMD FIT, Germany
 +
|-
 +
|Diane Litman          ||AT&T Research, USA
 +
|-
 +
|Pattie Maes          ||MIT Media Lab, USA
 +
|-
 +
|Uwe Malinowski        ||Siemens Corporate R&D, Germany
 +
|-
 +
|Gordon McCalla        ||University of Saskatchewan, Canada
 +
  |-
 +
|Michael McTear        ||University of Ulster, UK
 +
  |-
 +
| Alessandro Micarelli || University of Rome 3, Italy
 +
  |-
 +
| Robert J. Mislevy    ||Educational Testing Service, USA
 +
  |-
 +
| Riichiro Mizoguchi    ||Osaka University, Japan
 +
  |-
 +
| Edie M. Rasmussen    ||University of Pittsburgh, USA
 +
  |-
 +
| John Self            ||University of Leeds, UK
 +
  |-
 +
| Julita Vassileva      ||Federal Armed Forces Univ., Germany
 +
  |-
 +
|Wolfgang Wahlster    || DFKI, Germany
 +
  |-
 +
| Geoff Webb            ||Deakin University, Australia
 +
  |-
 +
| Ingrid Zukerman      || Monash University, Australia
 +
|-
 +
|
 +
|-
 +
|Doctoral Consortium Organizers:
 +
|-
 +
|Nadja De Carolis      ||University of Bari, Italy
 +
  |-
 +
|Fiorella de Rosis    ||University of Bari, Italy
 +
|-
 +
|
 +
|-
 +
|Workshop Coordinator:
 +
  |-
 +
|Christoph G. Thomas  ||GMD FIT, Germany
 +
|-
 +
|
 +
|-
 +
|Demonstration Organizer:
 +
|-
 +
|Giorgio Brajnik      ||University of Udine, Italy
 +
|}
 +
 +
 +
UM97 is being organized jointly by the Department of
 +
 +
Mathematics and Computer Science of the University of Udine, the
 +
 +
Department of Scientific Disciplines of the University of Rome 3,
 +
 +
the Department of Informatics of the University of Bari, and CRS4
 +
 +
(Center for Advanced Studies, Research and Development in
 +
 +
Sardinia), under the auspices of User Modeling, Inc.
 +
 +
 +
<p>———————— BRIEF SUBMISSION INSTRUCTIONS —————————</p>
 +
 +
PAPERS AND POSTERS
 +
 +
 +
Submissions are invited that describe original academic or
 +
 +
industrial research on some aspect of user modeling.
 +
 +
 +
Papers should describe significant, mature research; they will
 +
 +
be published in full length in the proceedings and presented in
 +
 +
talks at the conference.
 +
 +
 +
Posters typically describe research which does not yet
 +
 +
represent a substantial advance but which can stimulate the
 +
 +
exchange of ideas.  Summaries of posters will be included in the
 +
 +
proceedings.
 +
 +
 +
The timetable and the length requirements for poster and paper
 +
 +
submissions are the same.  Submissions to the poster category may
 +
 +
make more use of graphics and tables than is usual for paper
 +
 +
submissions, but they must be self-explanatory. If the authors do
 +
 +
not indicate a preference for the paper or poster category, the
 +
 +
program committee will judge which category is more appropriate.
 +
 +
 +
Submissions must fit within 12 single-spaced pages printed with
 +
 +
a 12-point font. These 12 pages must include all elements of the
 +
 +
submission. Page 1 must include the title of the paper, a short
 +
 +
abstract (150 words), a list of keywords, and the authors' postal
 +
 +
and e-mail addresses and fax and phone numbers. The abstract and
 +
 +
the author information on Page 1 must also be included in an
 +
 +
e-mail message that is sent to the program co-chairs one week
 +
 +
before the submission of the manuscript.
 +
 +
 +
A manuscript can be submitted either electronically (as a
 +
 +
PostScript file) or as hard copy. Details of the procedure for
 +
 +
electronic submission will be found in the full submission
 +
 +
instructions for UM97, which authors can obtain via the
 +
 +
conference Web site or by e-mail from the program co-chairs.
 +
 +
 +
All authors should obtain these full submission instructions,
 +
 +
which will also contain information about style files designed to
 +
 +
facilitate manuscript preparation and general tips on how to
 +
 +
maximize the likelihood of acceptance.
 +
 +
 +
DOCTORAL CONSORTIUM
 +
 +
 +
The doctoral consortium will offer PhD students a chance to
 +
 +
discuss their plans and the intermediate results of their
 +
 +
research with a diverse and knowledgeable international audience.
 +
 +
 +
Summaries of the accepted presentations will be included in the
 +
 +
proceedings volume.
 +
 +
 +
Further information on the doctoral symposium, including
 +
 +
information about possible sources of funding, can be obtained
 +
 +
via the UM97 Web site and by e-mail from the doctoral consortium
 +
 +
organizers.
 +
 +
 +
WORKSHOPS
 +
 +
 +
Half-day workshops will permit discussion and debate on topics
 +
 +
of current interest.  The format for each workshop will be
 +
 +
 +
determined by the proposer of that workshop, who will also set
 +
 +
any necessary deadlines for participants. Before submitting a
 +
 +
proposal, each proposer should obtain instructions and advice via
 +
 +
the conference Web site and/or by e-mail from the UM97 workshop
 +
 +
coordinator.
 +
 +
 +
SYSTEM DEMONSTRATIONS
 +
 +
 +
Various platforms will be available for unrefereed system
 +
 +
demonstrations. Prospective presenters should contact the
 +
 +
demonstration organizer by e-mail and specify their hardware and
 +
 +
software requirements.
 +
 +
<p>——————————— CONTACT ADDRESSES ————————————</p>
 +
 +
Up-to-date conference information and detailed submission
 +
 +
instructions can be obtained via either of the following World
 +
 +
Wide Web sites:
 +
 +
 +
http://www.cs.uni-sb.de/UM97/ (site in Germany) or
 +
 +
http://www.crs4.it/UM97/      (site in Sardinia)
 +
 +
 +
The following addresses can be used for queries and (where
 +
 +
applicable) for submissions:
 +
 +
 +
ORGANIZING CHAIR
 +
 +
 
 +
um97-organization@cs.uni-sb.de
 +
 +
Fax: Alessandro Micarelli, +39-6-5573030
 +
 +
 +
PROGRAM CO-CHAIRS:
 +
 +
 
 +
um97-papers@cs.uni-sb.de
 +
 +
Hard-copy submissions:
 +
 +
Anthony Jameson
 +
   
 +
Department of Computer Science
 +
   
 +
University of Saarbruecken
 +
   
 +
Stuhlsatzenhausweg, Building 36.1
 +
   
 +
66125 Saarbruecken, Germany
 +
   
 +
Phone: +49-681-302-2474
 +
 +
 +
DOCTORAL CONSORTIUM ORGANIZERS
 +
 +
um97-doctoral@cs.uni-sb.de
 +
 +
 +
WORKSHOP COORDINATOR
 +
 +
um97-workshops@cs.uni-sb.de
 +
 +
 +
DEMONSTRATION ORGANIZER
 +
 +
um97-demos@cs.uni-sb.de
 +
 +
<p>———————————— IMPORTANT DATES ————————————</p>
 +
 +
 +
{|
 +
|PAPERS AND POSTERS
 +
|-
 +
| ||
 +
|-
 +
| Monday,              ||  Receipt by e-mail of abstracts and
 +
  |-
 +
|25 November 1996        ||author information
 +
|-
 +
| ||
 +
|-
 +
| Monday,                || Receipt of electronic submissions
 +
|-
 +
|  2 December 1996        ||(optional)
 +
|-
 +
| ||
 +
|-
 +
| Tuesday,              || E-mail notification to authors if the
 +
|-
 +
| 3 December 1996        || requirement of hard-copy submission is waived
 +
|-
 +
| ||
 +
|-
 +
| Friday,                ||Receipt of 5 hard copies of each
 +
|-
 +
| 6 December 1996        ||<p>manuscript (except where the hard-copy requirement was waived on 3 December)</p>
 +
|-
 +
| ||
 +
  |-
 +
|Wednesday,            ||  Notification of authors by e-mail about
 +
|-
 +
|  26 February 1997      || acceptance or rejection of submissions
 +
|-
 +
| ||
 +
|-
 +
| Monday,                || Receipt of electronic versions of
 +
|-
 +
| 31 March 1997          || camera-ready papers and summaries of  posters
 +
  |-
 +
| ||
 +
 +
  |-
 +
|DOCTORAL CONSORTIUM
 +
  |-
 +
| ||
 +
  |-
 +
| Wednesday,              ||Receipt by e-mail of 3-page submissions
 +
    |-
 +
|5 February 1997        ||as ASCII text
 +
  |-
 +
| ||
 +
  |-
 +
| Wednesday,              ||Notification to authors by e-mail about
 +
  |-
 +
| 5 March 1997          || acceptance or rejection of submissions
 +
  |-
 +
| ||
 +
  |-
 +
| Monday,                ||Receipt of electronic versions of
 +
    |-
 +
|31 March 1997          || camera-ready summaries of presentations
 +
  |-
 +
| ||
 +
  |-
 +
|WORKSHOPS
 +
  |-
 +
| ||
 +
  |-
 +
| Monday,                || Receipt by e-mail of 3-page workshop
 +
  |-
 +
| 20 January 1997        || proposals as ASCII text
 +
  |-
 +
| ||
 +
  |-
 +
| Friday,              ||  Notification by e-mail to workshop
 +
  |-
 +
| 14 February 1997      || proposers about acceptance or rejection of proposals
 +
  |-
 +
| ||
 +
  |-
 +
| Friday,                || Submission, by proposers of accepted
 +
  |-
 +
| 21 February 1997        ||workshops, of final calls for participation
 +
  |-
 +
| ||
 +
  |-
 +
| Tuesday,              || Availability via the UM97 Web site
 +
  |-
 +
| 25 February 1997        ||and by e-mail of calls for participation in workshops
 +
  |-
 +
| ||
 +
  |-
 +
|SYSTEM DEMONSTRATIONS
 +
  |-
 +
| ||
 +
    |-
 +
|Tuesday,              || Registration of system demonstrations
 +
  |-
 +
| 15 April 1997          ||by e-mail
 +
|}
 +
 +
------------------------------------------------------------------
 +
 +
 +
<p>======================================================================</p>
 +
Topic 2:
 +
 +
Subject: Generation thesis available
 +
 +
Date:    20 June 1996
 +
 +
From:    Manfred Stede <stede@cs.tu-berlin.de>
 +
 +
 +
Manfred Stede: Lexical semantics and knowledge representation in
 +
 +
multilingual sentence generation.
 +
 +
University of Toronto, Dept. of Computer Science, 1996.
 +
 +
 +
This thesis develops a new approach to automatic language generation
 +
 +
that focuses on the need to produce a range of different {\em
 +
 +
paraphrases} from the same input representation.  One feature of the
 +
 +
system is its solidly grounding representations of word meaning in a
 +
 +
background knowledge base, which enables the production of paraphrases
 +
 +
stemming from certain inferences, rather than from purely lexical
 +
 +
relationships alone.
 +
 +
 +
The system is designed in such a way that the paraphrasing mechanism
 +
 +
extends naturally to a {\em multilingual} generator; specifically, we
 +
 +
will be concerned with producing English and German sentences.  The
 +
 +
focus of the system is on {\em lexical} paraphrases, and one of the
 +
 +
contributions of the thesis is in identifying, analyzing and extending
 +
 +
relevant linguistic research so that it can be used to handle the
 +
 +
problems of lexical semantics in a language generation system.  The
 +
 +
{\em lexical entries} are more complex than in previous generators,
 +
 +
and they separate the various aspects of word meaning, so that
 +
 +
different ways of paraphrasing can be systematically related to the
 +
 +
different motivations for saying a sentence in a particular way.  One
 +
 +
result of accounting for lexical semantics in this fashion is a
 +
 +
formalization of a number of {\em verb alternations}, for which a
 +
 +
generative treatment is given.
 +
 +
 +
While the actual {\em choice} of one paraphrase as the best-suited utterance
 +
 +
in a given situation is not a focal point of the thesis, two dimensions
 +
 +
of {\em preferring} a variant of a sentence are discussed: that of
 +
 +
assigning {\em salience} to the different elements of the sentence, and
 +
 +
that of {\em connotational} or {\em stylistic} features of the utterance.
 +
 +
These dimensions are integrated into the system, and it can thus
 +
 +
determine a preferred paraphrase from a set of alternatives.
 +
 +
 +
To demonstrate the feasibility of the approach, the proposed
 +
 +
generation architecture has been implemented as a protoype, along with a
 +
 +
domain model  that serves as the background knowledge base for specifying
 +
 +
the input to the generator.  A range of generated examples is presented
 +
 +
to show the functionality of the system.
 +
 +
 +
> If interested in either a hardcopy or a postscript file, please
 +
 +
> contact the author at stede@cs.tu-berlin.de
 +
 +
 +
<p>======================================================================</p>
 +
Topic 3:
 +
 +
Subject: Call for Participants TALC96 - Teaching and Language Corpora
 +
 +
Date:    Lanncaster University, UK, 9th-12th August, 1996
 +
 +
From:    "Mr S P Botley" <spb@comp.lancs.ac.uk>
 +
 +
 +
<center> CALL FOR PARTICIPANTS</center>
 +
 +
<center>TALC96 - TEACHING AND LANGUAGE CORPORA</center>
 +
 +
<center>Lancaster University, UK, 9th-12th August, 1996</center>
 +
 +
<center><http://www.comp.lancs.ac.uk/computing/research/ucrel/talc/></center>
 +
 +
 +
AIMS OF THE CONFERENCE
 +
 +
While the use of computer text corpora in research is now well
 +
 +
established, they are now being used increasingly  for teaching
 +
 +
purposes.  This includes the use of corpus data to inform and create
 +
 +
teaching materials; it also  includes the direct exploration of corpora
 +
 +
by students, both in the study of linguistics and of foreign languages.
 +
 +
 +
Talc96 will build upon the success of Talc94, which brought together
 +
 +
researchers and teachers who are involved in such work, to take part in
 +
 +
an international exchange of current experience and expertise.
 +
 +
 +
THEMES
 +
 +
KEY THEME: Talc96 will have a special focus on evaluating the claims
 +
 +
made for corpora in linguistics and language teaching.
 +
 +
 +
OTHER THEMES: which the conference is expected to cover include -
 +
 +
 +
1.) The use of corpora in student led learning and investigation.
 +
 +
2.) Software for corpus based language and linguistics learning.
 +
 +
3.) Developing corpora for teaching purposes.
 +
 +
4.) The exploitation of corpus based teaching and learning materials.
 +
 +
5.) The theory and practice of corpus based teaching and learning.
 +
 +
 +
WORKSHOPS
 +
 +
Talc96 will also host several workshops related to teaching and
 +
 +
language corpora. To give an example of what those workshops may be,
 +
 +
Talc94 had a variety of workshops such as "Multilingual Corpus
 +
 +
Building" and "Concordancing and Corpus Retrieval".  Workshops will be
 +
 +
of one to two hour duration.
 +
 +
 +
<center><u>TALC96 - Programme of Events</u></center>
 +
 +
 +
Is available at <http://www.comp.lancs.ac.uk/computing/research/ucrel/talc/>
 +
 +
 +
Please register BEFORE 21st July 1996, otherwise we cannot guarantee
 +
 +
availability of accommodation.
 +
 +
 +
 +
<p>======================================================================</p>
 +
Topic 4:
 +
 +
Subject: KBCS-96 (2nd CFP) Deadline Extended
 +
 +
Date:    Wed, 26 Jun 1996 - Deadline 15 August 1996
 +
 +
From:    KBCS Word Processing <kbcs@konark.ncst.ernet.in>
 +
 +
                            <center> Second Call for Papers</center>
 +
 +
                          <center>INTERNATIONAL  CONFERENCE ON</center>
 +
 +
                        <center> KNOWLEDGE BASED COMPUTER SYSTEMS</center>
 +
 +
                    <center> National Centre for Software Technology</center>
 +
 +
                              <center>    Bombay, India</center>
 +
 +
                            <center>  December 16-18, 1996</center>
 +
 +
 +
 +
THE DEADLINE FOR SUBMISSION OF PAPERS HAS NOW BEEN EXTENDED TO AUGUST 15, 1996
 +
 +
                <center>URL : http://konark.ncst.ernet.in/~kbcs/kbcs96.html</center>
 +
____________________________________________________________________________
 +
The International Conference on Knowledge Based Computer  Systems will be held
 +
 +
in  Bombay, India during December 16-18, 1996.  The conference is intended to
 +
 +
act as  a  forum for promoting  interaction among  researchers in the field of
 +
 +
Artificial  Intelligence  in  India  and  abroad.  There  will  be  a two  day
 +
 +
conference    during    December  16-17,  1996    followed  by  one  day  of
 +
 +
post-conference tutorials  on December 18, 1996.
 +
 +
 +
Papers are  invited on  substantial, original  and unpublished  research  on
 +
 +
all aspects of Artificial  Intelligence, including, but  not limited to  the
 +
 +
following:
 +
{|
 +
|o AI Applications              ||o AI Architectures
 +
|-
 +
|o Artificial Life              ||o Automatic Programming
 +
|-
 +
|o Cognitive Modeling          ||o Expert Systems
 +
|-
 +
|o Foundations of AI            ||o Genetic Algorithms
 +
|-
 +
|o Information Retrieval        ||o Intelligent Tutoring Systems
 +
|-
 +
|o Knowledge Acquisition        ||o Knowledge Representation
 +
|-
 +
|o Machine Learning            ||o Machine Translation
 +
|-
 +
|o Natural Language Processing  ||o Neural Networks
 +
|-
 +
|o Planning and Scheduling      ||o Reasoning
 +
|-
 +
|o Robotics                    ||o Search Techniques
 +
|-
 +
|o Speech Processing            ||o Theorem Proving
 +
|-
 +
|o Uncertainty Handling        ||o User Interfaces
 +
|-
 +
|o User Modeling                || o Vision
 +
|}
 +
 +
 +
Programme Committee:
 +
 +
 +
{|
 +
|S. Arunkumar, IIT, Bombay              ||Amitava Bagchi, IIM, Calcutta
 +
|-
 +
|Pushpak Bhattacharya, IIT, Bombay      ||Margaret A. Boden, U of Sussex, UK
 +
|-
 +
|Nick Cercone, U of Regina, Canada      ||B. B. Chaudhuri, ISI, Calcutta
 +
|-
 +
|R. Chandrasekar, NCST, Bombay          ||S. K. Goyal, GTE Labs , USA
 +
|-
 +
|S. S. Gupta, TUL, Bombay              ||J. R. Isaac, NIIT, New Delhi
 +
|-
 +
|Aravind K. Joshi,                      ||R. A.  Kowalski, Imperial College, UK
 +
|-
 +
|U of Pennsylvania, USA
 +
|-
 +
|H. N. Mahabala, INFOSYS, Bangalore    ||M. Narasimha Murthy, IISc, Bangalore
 +
|-
 +
|R. Narasimhan, CMC, Bangalore          ||S. Ramani, NCST, Bombay (Chair)
 +
|-
 +
|P. V. S. Rao, TIFR, Bombay            ||Patrick Saint-Dizier,U of Paul Sabatier, France
 +
 +
|-
 +
|R. Sangal, IIT, Kanpur                ||R. Uthurusamy, GMR, USA
 +
|-
 +
|M. Vidyasagar, CAIR, Bangalore
 +
|}
 +
Format of Submission:
 +
 +
 +
Authors should submit  their papers,  not  to exceed  5000 words  (including
 +
 +
figures and  references) either  electronically or  in hard  copy.    Papers
 +
 +
should be in English.  Papers should include  an abstract of about  100-200
 +
 +
words in  length.    Papers  outside the  specified  length are  subject  to
 +
 +
rejection without review.  Since  reviewing will be  "blind", the  authors'
 +
 +
names and affiliations along with the main area of the paper should be given
 +
 +
only on a separate cover sheet.  Hard copy submissions should  be sent in
 +
 +
triplicate.  Papers in  electronic form can be in any of the following
 +
 +
formats:  plain text, Postscript, Latex, Microsoft Word, or Wordstar.
 +
 +
Submissions in electronic form are preferred.
 +
 +
 +
Send papers to the KBCS-96 Secretariat at the address below.
 +
 +
 +
Paper Submission Deadlines:
 +
 +
o  Papers due:  August 15, 1996
 +
 +
o  Acceptance Notification:  October 15, 1996
 +
 +
o  Camera Ready Copy due:  December 1, 1996
 +
 +
 +
Call for Tutorials:
 +
 +
 +
Proposals are  invited for  post-conference  tutorials.  Tutorials  can  be
 +
 +
half-day  or full-day,  and  will be  held  on December  18th,  1996.    The
 +
 +
proposal should be presented  in the form of  a 200-word abstract, one  page
 +
 +
topical outline  of the  content,  description of  the proposers  and  their
 +
 +
qualifications relating to the tutorial content.
 +
 +
 +
Tutorial Submission Deadlines:
 +
 +
 +
o  Proposal Submission:  July 31, 1996
 +
 +
o  Acceptance Notification:  August 31, 1996
 +
 +
o  Complete Tutorial materials due:  December 1, 1996
 +
 +
 +
Send proposals to the KBCS-96 Secretariat at the address below.
 +
 +
 +
Organizing Committee:
 +
 +
{|
 +
|George Arakal, NCST (Chair)  ||K.S.R. Anjaneyulu, NCST
 +
|-
 +
|P. Ravi Prakash, NCST        ||Durgesh D. Rao, NCST
 +
|-
 +
|M. Sasikumar, NCST          ||T. Suresh, NCST
 +
|}
 +
 +
 +
For further information  please refer to  the KBCS-96 home  page or
 +
 +
write  to the KBCS-96 Secretariat.
 +
 +
___________________________________________________________________________
 +
 +
Address
 +
 +
{|
 +
|KBCS-96 Secretariat                    || Phone :  +91 (22) 620 1606
 +
|-
 +
|National Centre for Software Technology  ||Fax :  +91 (22) 621 0139
 +
|-
 +
|Gulmohar Cross Rd No.  9                ||E-mail :  kbcs@konark.ncst.ernet.in
 +
|-
 +
|Juhu, Bombay 400 049, India
 +
|}
 +
 +
URL : http://konark.ncst.ernet.in/~kbcs/kbcs96.html
 +
<p>——————————————————————————————————————</p>
 +
 +
<p>======================================================================</p>
 +
eof
 +
<p>======================================================================</p>

Latest revision as of 06:07, 15 November 2015

Siggen logo small.JPG

The following issues of the SIGGEN newsletter are available:

2005

Issue 1

SIGGEN Newsletter

www.siggen.org

Date: 05 June 2005


TOPICS:

1. INF: Recent SIGGEN updates; board election, state of SIGGEN

2. CfB: Call for Bids for INLG'06

3. CfP: EWNLG'05 in Aberdeen [Early Registration by June 17]

4. CfP: Symposium on Dialog Modeling and Generation [July 7]

5. CfP: Using Corpora for Natural Language Generation [July 14]

6. TUT: Statistical Machine Translation and Generation [Aug. 11]

7. JOB: Postdoctoral Position in Adaptive Spoken Language, NY

8. JOB: Research Fellow/PostDoc, Aberdeen

9. Stu: Funded Studentship, Aberdeen

10. ANN: Surge 2.3 now available


SIGGEN Board Members:

Tilman Becker Tilman.Becker(at)dfki(dot)de
Charles Callaway ccallawa(at)inf(dot)ed(dot)ac(dot)uk
Irene Langkilde-Geary irenelg(at)cs(dot)byu(dot)edu
David McDonald dmcdonald(at)bbn(dot)com
David Reitter dreitter(at)inf(dot)ed(dot)ac(dot)uk


TOPIC 1: Recent SIGGEN updates; board election, state of SIGGEN

Dear SIGGEN members,

Tilman Becker, the last remaining member from the previous SIGGEN board, has been joined by the 4 new board members from this winter's election: Charles Callaway, Irene Langkilde-Geary, David McDonald, and student representative Dave Reitter.

As mentioned before, the website has been moved to www.siggen.org, (change your bookmarks!) hosted at DFKI, and has been updated, most significantly in regards to the membership on the Who's who page. This page, which now lists 145 members, has been revamped to ensure that all links are valid. If you, or someone you know, would like to be added to this list, please don't hesitate to email us. The mailing list has been similarly checked to ensure valid email addresses, and now contains 209 members. This means that those who do not receive copies of this newsletter are not currently on the email list, not considered to be members, and thus cannot vote in future elections. (A copy of the current SIGGEN constitution is located at: http://www.siggen.org/discussion/constitution/constitution_v2.html)

Your board members will be attending a wide array of conferences this summer, so if you see us, please don't hesitate to talk to us, or of course send us email. We will quickly respond to any suggestions or comments you may have.

-- The SIGGEN Board


TOPIC 2: SIGGEN: Call for Bids to Host INLG-2006

http://www.siggen.org/event/bidinlg06.html

SIGGEN (Special Interest Group in Generation of the Association for Computational Linguistics) invites proposals to host the International Natural Language Generation (INLG) Conference in 2006. INLG conferences are usually held in the summer, and sometimes co-located with other NLP events, such as ACL. INLG attendance is usually on the order of 80 people (that is, more than 50 and less than 120).

As INLG-2004 was in the ACL European region, we especially welcome and will prefer proposals for holding INLG-2006 in the ACL Americas or Asia/Pacific regions.

Draft proposals should be emailed to ccallawa(at)inf(dot)ed(dot)ac(dot)uk by 30 Sept 2005.

These proposals should outline:

* conference location and practicalities (venue, accomodation, meals). Note that INLG's have traditionally been held in places which are secluded but easily accessible (within a few hours drive of a major international airport), such as Brighton, UK (2004); mid-State New York (2002); Mitzpe Ramon, Israel (2000); Niagara-on-the-Lake, Canada (1998); Hertsmonceux Castle, UK (1996); and Kennebunkport, USA (1994).

* approximate conference date. Will it be possible for INLG attendees to combine attendance at INLG with attendance at other conferences of interest to the NLG community (for example, INLG-02 immediately preceded ACL-02, INLG-98 immediately preceded ACL-98, and INLG-92 immediately followed ANLP-92).

* rough budget and expected sponsorship. Approximately how much will participants need to pay to attend, including accomodation and meals as well as conference registration? Note that attendance cost for previous INLG's has generally been US$500 or less.

* local arrangements. Who will be in charge of organising the conference, and how will finances be handled (eg, can participants pay by credit card)?

Draft proposals will be considered by a committee that includes some SIGGEN board members and previous INLG chairs. This committee may contact proposers and request additional information.

For more information, see:

* http://www.itri.brighton.ac.uk/inlg04/ for information about INLG-2004.

* http://inlg02.cs.columbia.edu/ for information about INLG-2002.

* http://www.dfki.de/~wahlster/bids/ for draft bids for ACL-01 (a bit different from INLG draft bids, but useful as examples).


TOPIC 3: EWNLG'05 in Aberdeen [Early Registration by June 17]

Call for Participation

8-10 August 2005 Aberdeen, Scotland (following IJCAI-2005 in Edinburgh) http://www.ling.helsinki.fi/~gwilcock/ENLG-05/

Natural language generation (NLG) is a subfield of natural language processing that focuses on the generation of written texts in natural languages from some underlying non-linguistic representation of information, generally from databases or knowledge sources. Accomplishing this goal may be envisioned for a number of different purposes, including standardized and/or multi-lingual reports, summaries, machine translation, dialogue applications, and embedding in multi-media and hypertext environments. Consequently, the automated production of language is associated with a large number of highly diverse tasks whose appropriate orchestration in high quality poses a variety of theoretical and practical problems. Relevant issues include content selection, text organization, production of referring expressions, aggregation, lexicalization, and surface realization, as well as coordination with other media.

The workshop continues a biennial series of workshops on natural language generation that has been running since 1987. Previous European workshops have been held at Royaumont, Edinburgh, Judenstein, Pisa, Leiden, Duisburg, Toulouse (2001) and Budapest (2003). The series provides a regular forum for presentation of research in this area, both for NLG specialists and for researchers who may not think of themselves as part of the NLG community.

The 2005 workshop will span the interest areas of natural language generation and Artificial Intelligence, with a special focus on research that integrates NLG with AI, including vision, robotics, intelligent agents, and knowledge discovery. We also encourage papers that investigate the use of state-of-the-art generation technology in real world applications to handle both spoken and text output, and apply language generation techniques to interactive AI systems like communicating robots, to allow the user to enter into short conversations with the system in search for information. There will be demonstrations of working NLG systems, and special sessions for posters describing real-world applications and advanced language technology systems.

Papers will be presented on formal, corpus-based, implementational and analytical work on conventional NLG topics (realisation, microplanning, etc), and especially papers with a focus on the following themes:

* Embodied agents and robot communication (special track)

* NLG for real-world applications

* Use of ontologies in NLG

* Statistical methods for NLG

* Information organization for planning and NLG

* Robust methods and techniques for NLG

* Evaluation of NLG systems

Invited Speaker:

Kevin Knight (Information Sciences Institute, University of Southern California) will give an invited talk on Tree Transducers for Machine Translation and Generation


TOPIC 4: Symposium on Dialogue Modelling and Generation

Call for Participation

July 7, Amsterdam, The Netherlands

http://lubitsch.lili.uni-bielefeld.de/DMG/

This symposium is intended to tackle issues in the semantics and pragmatics of dialogue and dialogue generation. It aims at bringing together the dialogue modelling and language generation/production communities and will provide an opportunity for researchers from a variety of disciplines, including linguistics, computer science and psycholinguistics, to exchange ideas.

We invited talks elaborating on important theoretical notions in dialogue modelling -such as constraints (Asher & Lascarides, 2003, and many other recent papers), the role of domain knowledge (e.g., Ludwig, 2003, and, again, many more) and the influence of social relations between interlocutors on dialogue behaviour (going back to the seminal work by Brown and Levinson, 1978)- and asked presenters to shed light on these or other theoretically fruitful notions in dialogue modelling by:

* relating them to issues in language generation/production or

* drawing out similarities and differences between applications of such notions in discourse generation versus interpretation or

* describing computational/implemented models, in particular, for generation/production or

* comparing psycholinguistic with linguistic or engineering approaches to dialogue modelling.

The symposium will thus be a natural complement to ones that deal with natural language interpretation or structural properties of discourse.


TOPIC 5: Using Corpora for Natural Language Generation

Call for Participation

July 14, Birmingham, England (preceding Corpus Linguistics 2005) http://www.itri.brighton.ac.uk/ucnlg/

We aim to bring together researchers who use corpora for NLG research either in the traditional, manual way, or automatically, involving machine learning and statistical methods. The goal of the workshop is to present and discuss current research, to compare manual and automatic corpus exploitation, to evaluate achievements, and to identify challenges for the future.

Registration is open at the Corpus Linguistics 2005 website. Please note that Using Corpora for NLG is a full-day workshop, and that you do not need to register for the main conference. Simply select the appropriate options in the registration form. The workshop registration fee is 70 Pounds.

Papers will be presented on all aspects of using corpora for natural language generation, including, but not limited to:

* (Partial) automation of traditional corpus analysis for NLG

* Issues in annotating corpora for NLG

* Statistical approaches to deep and/or surface generation

* Machine learning methods for deep and/or surface generation

* Role of corpora in the evaluation of NLG systems

* Reuse of resources developed for NLU (e.g. treebanks) in NLG

* Domain-specific vs. general purpose corpora for NLG

We would like to emphasise that where we say `NLG' we mean to include the language generation components of machine translation and dialogue systems.

Invited Speaker:

Irene Langkilde-Geary (Brigham Young University, Provo, USA) will give an invited talk with the provisional title: Constraint programming as a Whiteboard Architecture for Probabilistic NLG.

Panel on Exploiting Corpora for NLG:

We will hold a panel discussion on the topics of the workshop. The panel members are:

Chris Brew, Linguistics, Ohio State University, USA

Irene Langkilde-Geary, Brigham Young University, USA

Ehud Reiter, Computing Science, University of Aberdeen, UK

Donia Scott, CRC, Open University, UK

Bonnie Webber, Informatics, University of Edinburgh, UK


TOPIC 6: Tutorial: Statistical Machine Translation and Generation

August 11, Aberdeen, Scotland (Immediately following EWNLG'05)

http://www.csd.abdn.ac.uk/~cmellish/knight.html

Kevin Knight, USC/Information Sciences Institute, USA

The statistical approach to machine translation provides a set of techniques for (1) automatically learning translation knowledge from bilingual data, and (2) applying that knowledge to translate previously-unseen sentences. When it was first introduced, statistical MT was far too slow and inaccurate to be useful -- it was an interesting lab experiment. In 2005, we see statistical MT significantly outperforming other methods in many language pairs and domains, at speeds permitting commercial applications like foreign news broadcast translation. What made this possible? This tutorial will cover the basic theory and the major technical advances of the past few years. Of course, there is a long way to go! The tutorial will also cover known limitations of current MT models and describe current research trends. We will also discuss problems in natural language generation, where the input is typically more abstract than foreign text, and describe how statistical MT research is currently exploiting linguistic categories.

This tutorial is free of charge. It is hosted by the Natural Language Generation group at the University of Aberdeen. We are grateful for the support of EPSRC grant EP/C523156/1 which has made this tutorial possible.

If you are interested in attending this tutorial, please send an email to ccameron(at)csd(dot)abdn(dot)ac(dot)uk so that you can be allocated a place and informed of any further developments. For more information, contact Chris Mellish (cmellish(at)csd(dot)abdn(dot)ac(dot)uk).


TOPIC 7: Postdoctoral Position in Adaptive Spoken Language

StonyBrook, NY

The Psychology, Linguistics, and Computer Science Departments at Stony Brook University are collaborating on an innovative project, funded by the National Science Foundation: "Adaptive Spoken Dialog with Human and Computer Partners." We seek a postdoctoral associate to collaborate with us. The successful applicant will have a Ph.D. in Psychology, Linguistics, or Computer Science, or a relevant interdisciplinary field.

Preferred Qualifications: Experience in one or more of the following: experiment design, statistics, linguistic phonetics, computational linguistics, speech processing, psycholinguistics techniques such as eyetracking.

Depending on the candidate's background and qualifications, duties will include:

1) Contributing to empirical (laboratory and corpus-based) studies of language use (both comprehension and production). This involves working with human subjects, designing experiments, collecting data, and conducting detailed analyses of text and spoken corpora

2) Contributing to our efforts to model human language behavior and test computational models using data.

3) Generating independent sub-projects relevant to project's research questions.

4) Supervising graduate and undergraduate student researchers in day-to-day activities across one or more projects conducted within the PI's laboratories

5) Assisting with management of laboratory resources, such as ordering equipment, software installation, etc.

6) Writing up results for publication

7) Traveling to conferences and workshops as appropriate

8) Developing expertise in relevant techniques and procedures that span Psychology, Linguistics, and Computer Science

This is a full time position. The Research Foundation of SUNY is a private educational corporation. Employment is subject to the Research Foundation policies and procedures, sponsor guidelines, and availability of funding. Projected start date: January 1, 2006 (flexible)

Application Procedure: Applications will be accepted until the position is filled. More details about the project can be found at http://www.cs.sunysb.edu/~adaptation/. Applications for the may be submitted on-line at http://naples.cc.sunysb.edu/Admin/CampusJob.nsf via the "Postdoctoral positions" link, or else submit a cover letter and resume to:

Prof. Susan E. Brennan

Department of Psychology

Stony Brook University

Stony Brook, New York 11794-2500

Fax: 631-632-7876

Stony Brook University, flagship campus of the S.U.N.Y. system, is a world-class, student-centered research university located 60 miles from New York City.


TOPIC 8: Research Fellow/PostDoc: Towards a Unified Algorithm for the generation of referring expressions

University of Aberdeen, Scotland

Applications due: July 15, 2005

Contact: Dr Kees van Deemter

kvdeemte(at)csd(dot)abdn(dot)ac(dot)uk

Background:

Natural Language Generation programs generate text from an underlying Knowledge Base. It can be difficult to find a mapping from the information in the Knowledge Base to the words in a sentence. Difficulties arise, for example, when the Knowledge Base uses `names' (i.e., databases keys) that a hearer/reader does not understand. This can happen, for instance, if the Knowledge Base contains an artificial name like `#Jones083', because `Jones' alone is not uniquely distinguishing; it is also true if the Knowledge Base deals with entities for which no names at all are in common usage (e.g., a specific tree or a chair). In all such cases, the program has to "invent" a description that enables the reader to identify the referent. In the case of Mr. Jones, for example, the program could give his name and address; in the case of a tree, some longer description may be necessary (e.g., `the green oak on the corner of ... and ...'. The technical term for this set of problems is Generation of Referring Expressions (GRE). GRE is a key aspect of almost any Natural Language Generation system.

Aims:

Existing GRE algorithms tend to focus on one particular class of referring expressions, for example conjunctions of atomic or relational properties (e.g., `the black dog', `the book on the table'). Our research is aimed at designing and implementing a new algorithm for the generation of referring expressions that generates appropriate descriptions in a far greater variety of situations than any of its predecessors. The algorithm will be more complete than its predecessors because it is able to construct a greater variety of descriptions (involving negations, disjunctions, relations, vagueness, etc.). The descriptions generated should also be more appropriate (i.e., more natural in the eyes of a human hearer/reader), because the algorithm will be based on empirical studies involving corpora and controlled experiments. Among other things, these empirical studies will address the question under what circumstances the descriptions should be logically under- or overspecific; they will also allow us to prune the search space (i.e., the space of all descriptions) which would otherwise threaten to make the problem intractible. The project combines (psycho)linguistic, computational and logical challenges and should be of interest to people whose intellectual home is in either of these areas.

General Info:

http://www.itri.brighton.ac.uk/projects/tuna/TUNA-index.html


TOPIC 9: Funded Studentship: Managing Ambiguity in Generated Text

University of Aberdeen, Scotland

Applications due: July 15, 2005

Contact: Dr Kees van Deemter
kvdeemte(at)csd(dot)abdn(dot)ac(dot)uk


General Info for prospective students at Aberdeen:

http://www.abdn.ac.uk/sras/postgraduate/apply5


TOPIC 10: Surge 2.3 now available for download

Contact: Charles Callaway

ccallawa(at)inf(dot)ed(dot)ac(dot)uk

Surge 2.3, the latest version of the SURGE English grammar, has been packaged for download at the following location. Improvements have been made for written and spoken dialogue, XML and LATEX formatting, punctuation, and additional coverage rules derived from the Penn TreeBank. For use with FUF5.3.

http://homepages.inf.ed.ac.uk/ccallawa/index-c.html


--- eof ---

1999

Issue 2 (lost)

Issue 1 (lost)

1998

Issue 1

Date: 25 Mar 1998

TOPICS:

1. A: INLG Registration & Program [Act by May 1st 1998]

2. CFP: TAG+ Workshop [Philadelphia - Deadline Apr 15th 1998]

3. A: CSLU Spring Short Courses [Portland, OR - May 5 - May 18]

4. JOB: ITRI Brighton PhD Studentship [Apply by Apr 30, 1998]

5. CFP: COLING/ACL98 Discourse Relations Workshop [Deadline Apr 6]

6. CFP: Special issue NRHM Adaptivity and User Modeling [Deadline Jun 1]

7. CFP: Computational Treatment of Portuguese - Brazil [Deadline May 4]

8. A: KPML Mailing List

9. P: Diana McKinnie [Generating reports from dictated X-ray reports]


TOPIC 1:

A: INLG Registration & Program [Act by May 1st 1998]

From: Graeme Hirst <gh(at)cs(dot)toronto(dot)edu>


9th International Workshop on

NATURAL LANGUAGE GENERATION


5-7 August 1998


Prince of Wales Hotel

Niagara-on-the-Lake, Ontario, Canada


REGISTRATION INFORMATION


Preliminary details of the program and registration information and forms are now available for the 9th biennial Workshop on Natural Language Generation.

This message gives basic information on participation. For full information, please visit the INLG-98 Website:

http://logos.uwaterloo.ca/~inlg98


PROGRAM AND SCHEDULE:

The workshop will begin with an opening reception on the evening of Tuesday 4 August, and end with lunch on Friday 7 August.

The program includes approximately 30 papers, demonstrations, and a panel session to be presented over 2 1/2 days. (The complete list of accepted papers is on the conference Web site.)

In addition, the social program includes an outing to Niagara Falls with dinner at the top of the Skylon Tower.


LOCATION AND TRANSPORTATION:

The workshop will be held at the Prince of Wales Hotel, in the scenic town of Niagara-on-the-Lake, which is easily accessible from Toronto International Airport. See our Web page on transportation for details of transfers to Niagara-on-the-Lake from Toronto International Airport, on Buffalo Airport as an alternative, and for directions to Niagara-on-the-Lake by car, bus, and train.


REGISTRATION AND ACCOMMODATION:

A discount accommodation-and-meal package has been negotiated with the Prince of Wales Hotel for the workshop. To get the discount, you must book your accommodation on the conference registration form, which is available from our Web site.


Registration paid by credit card will be accepted by e-mail and fax.


NOTE!!! Space at the workshop is limited. We will allocate space in the order that registrations are received, except that a space will be held for one author of each submitted paper (whether accepted or not) until **1 May 1998**. If the workshop is oversubscribed before the final June deadline, we will endeavour to find additional space, but cannot promise to succeed nor that any space found will be as cheap as the reserved space. Workshop registration and hotel reservations must be received by **1 June 1998**. Any unassigned hotel rooms will be released after this date. Late registrants will be accommodated only if space is available, and will have to pay the hotel's full rack rates.


FINANCIAL ASSISTANCE:

We anticipate having funds to subsidize attendance at the workshop by graduate students and unfunded researchers. Details should be known by mid-April.


TOURISM:

See the INLG Web pages for links to information on tourism in the Niagara region, Toronto, and Montreal.


TRANSPORTATION TO MONTREAL FOR COLING:

The workshop is to be held in the week immediately prior to the joint conference of COLING and ACL, in Montreal, Canada (10-14 August 1998). After the workshop, a bus will take participants who wish to attend COLING / ACL directly to the Toronto train station for an express train to Montreal.


WORKSHOP SPONSOR AND ORGANIZERS:

The workshop is sponsored by the Association for Computational Linguistics and ACL SIGGEN (Special Interest Group on Natural Language Generation).

The workshop is organized by Chrysanne DiMarco of the University of Waterloo, with the assistance of Graeme Hirst of the University of Toronto. The Program Chair is Eduard Hovy of USC/ISI.

General enquiries concerning registration and accommodation:

Jean Webster, University of Waterloo

jrwebster(at)icr(dot)uwaterloo(dot)ca

phone +1 519-888-4567 extension 5076.

General workshop questions:

Chrysanne DiMarco, University of Waterloo

cdimarco(at)logos(dot)uwaterloo(dot)ca

phone +1 519 888 4443


For more information, program, and registration forms, visit the INLG-98 Website:

http://logos.uwaterloo.ca/~inlg98



TOPIC 2:

CFP: TAG+ Workshop [Philadelphia - Deadline Apr 15th 1998]

From: Jennifer MacDougall <jmacdoug(at)central(dot)cis(dot)upenn(dot)edu>

TAG+ WORKSHOP -- FIRST CALL FOR PAPERS

August 1 to August 3, 1998

TAG TUTORIALS -- PRELIMINARY ANNOUNCEMENT

July 28 to July 31, 1998

Philadelphia, PA, USA

URL: http://www.cis.upenn.edu/~ircs/mol/tag98.html


The fourth workshop on tree-adjoining grammars and related frameworks (hence the + after TAG) will be held at the Institute for Research in Cognitive Science at the University of Pennsylvania in August 1998, from August 1 to August 3. Previous workshops were held at Dagstuhl (1990), UPenn (1992), and Univ. Paris 7 (1994).

Papers on all aspects of TAG (linguistic, mathematical, computational, and applicational), as well as papers relating TAGs to other frameworks, are invited. As in the past there will be some invited talks on other grammar formalisms which have interesting relationships to TAGs (for example, Categorial Grammars and HPSG).


GUIDELINES FOR ABSTRACTS:

Abstracts should be at most two pages (exclusive of references), and should be submitted in ASCII format, as a .ps file, or as SELF-CONTAINED latex file to jmacdoug (at) central (dot) cis (dot) upenn (dot) edu. (If email is not available, please send the abstract to the address given below.) Please indicate on the abstract if you would prefer to give a short presentation (10 minutes) or a long one (30 minutes). The abstract should contain your name, address, and email address. Proceedings including extended versions (4 pages) of accepted abstracts will be available at the workshop.

Deadline for submission for abstracts: April 15
Notification of acceptance: May 15
Deadline for submission of camera-ready
extended abstract: July 6
Workshop Dates: August 1 to August 3

If you do not want to submit an abstract, but would like to attend, we would appreciate it if you could inform us by email by July 6 (unless you have already done so). If you would like to present a demo, please let us know as soon as possible, including information about required hard and software.


PROGRAM COMMITTEE:

Anne Abeille (Universit'e Paris 7)

Tilman Becker (DFKI)

Christy Doran (University of Pennsylvania)

Robert Frank (Johns Hopkins University)

Klaus Netter (DFKI)

Richard Oehrle (University of Arizona)

Owen Rambow (CoGenTex, Inc.)

Giorgio Satta (Universita di Padova)

Yuka Tateisi (University of Tokyo)

K. Vijayshanker (University of Delaware)

David Weir (University of Sussex)


CONTACT ADDRESS:

Jennifer MacDougall

553 Moore Building

University of Pennsylvania

Philadelphia, PA 19104-6389

USA

Telephone: (215) 898-3191

FAX: (215) 898-0587

Email: jmacdoug (at) central (dot) cis (dot) upenn (dot) edu


TUTORIAL:

Prior to the workshop there will be a tutorial (including labs and demos) from July 28 to July 31 1998. Details about the tutorial will be sent out soon. We are trying to get some partial support for some of the students attending the tutorials. If you may be interested in attending this tutorial, please contact Jennifer MacDougall at the address above (preferably by email) and we will send you more information.


ORGANIZING COMMITTEE:

Anne Abeille (Paris 7)

Tilman Becker (DFKI)

Owen Rambow (CoGenTex, Inc.)

Giorgio Satta (Universita di Padova)

K. Vijayshanker (University of Delaware)

TOPIC 3:

A: CSLU Spring Short Courses [Portland, OR - May 5 - May 18]

From: "Terri Durham" <durham(at)cse(dot)ogi(dot)edu>

Institute in Portland, Oregon will be giving two spring short courses in May to coincide with the ICASSP '98 Conference in Seattle Washington.

Please visit our web page for a full description of each course and to fill out your registration form. http://www.cse.ogi.edu/CSLU/shortcourse2/

If you have any questions please don't hesitate to give me a call.

Thank You,

Terri Durham

CSLU Center Administrator


PO Box 91000 Portland, OR. 97291

20000 NW Walker Rd., Beaverton, OR. 97006

Phone: 503-690-1630 // Fax: 503-690-1306


May 5-8th Text-to-Speech Synthesis

Instructors:

Paul Taylor

Center for Speech Technology Research, University of Edinburgh

Alan Black

Center for Speech Technology Research, University of Edinburgh

Michael Macon

Center for Spoken Language Understanding, Oregon Graduate Institute


May 18-22 Building Spoken Dialogue Systems

Instructors:

Stephen Sutton

Center for Spoken Language Understanding, Oregon Graduate Institute

Teaching Assistants:

Andrew Cronk

Center for Spoken Language Understanding, Oregon Graduate Institute

Ed Kaiser

Center for Spoken Language Understanding, Oregon Graduate Institute


TOPIC 4: JOB: ITRI Brighton PhD Studentship [Apply by Apr 30, 1998]

From: postgrad-admissions(at)itri(dot)brighton(dot)ac(dot)uk


Information Technology Research Institute

University of Brighton

PhD Studentship for October 1998

Application deadline: 30 April 1998

The Information Technology Research Institute (ITRI) invites applications for a three-year EPSRC studentship award to commence in October 1998. The studentship will be awarded in one (or more) of the following topics in Computational Linguistics:


DOCUMENT GENERATION (including TEXT GENERATION): architectures; corpus analysis; diagrammatic reasoning; discourse; evaluation; hybrid generation; implementation; layout; multilinguality; multimodality; representation languages; pragmatics; tools

LEXICONS: corpus analysis; evaluation; lexical statistics; lexicalized grammars; lexicography; lexicon induction from text; multilinguality; representation; tools; tuning; word sense disambiguation

NATURAL LANGUAGE INTERFACES: dialogue; interface design


Applicants should have a good honours degree or equivalent in Computer Science, Computational Linguistics or Linguistics.

EPSRC studentships are restricted to UK or EU residents. Residents of the UK are eligible for fees and a maintenance allowance; other EU residents are only eligible for fees (and so would need to be able to support themselves during their studies).

The EPSRC baseline rate of maintenance allowance is currently approx 5,295 pounds sterling per annum. For further general information on EPSRC studentships, please consult http://www.epsrc.ac.uk/in-depth/indpfram.htm.

Further information on the Institute's research programme can be found on the ITRI home page (http://www.itri.brighton.ac.uk) and information about students and how to apply on our research students page (http://www.itri.brighton.ac.uk/students).

If we already have your application on file for consideration this year, you do not need to apply again.

Deadline for applications: 30 April 1998

For additional advice and information, please contact:

Ms. Vivienne Wicks, Research Administrator

Information Technology Research Institute

University of Brighton

Lewes Rd.

Brighton

BN2 4GJ, UK


Email: postgrad-admissions (at) itri (dot) brighton (dot) ac (dot) uk

Tel: +44 1273 642900

Fax: +44 1273 642908

TOPIC 5:

CFP: COLING/ACL98 Discourse Relations Workshop [Deadline Apr 6]

From: <stede(at)cs(dot)tu-berlin(dot)de>


Coling-ACL '98 workshop
"Discourse Relations and Discourse Markers”
August 15, 1998
Universit� de Montr�al
Montr�al/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 (at) isi (dot) 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(at)cs(dot)tu-berlin(dot)de wannerlo(at)informatik(dot)uni-stuttgart(dot)de


Timetable

Deadline for electronic submissions: April 6, 1998

Deadline for hardcopy submissions: April 9 (arrival date)

Notification of acceptance: May 25, 1998

Final manuscripts due: June 15, 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)

TOPIC 6:

CFP: Special issue NRHM Adaptivity and User Modeling [Deadline Jun 1]

From: Maria Milosavljevic <mariam(at)alba.nsw.cmis.CSIRO.AU>


The New Review of Hypermedia and Multimedia


1998 call for submissions on the themes of 'adaptivity and user modeling in hypertext/hypermedia systems', and 'hypermedia for museums and cultural heritage’.

NRHM (previously Hypermedia, one of the original journals on the subject) is a refereed annual review journal covering research on practical and theoretical developments in hypermedia, interactive multimedia and related technologies. The new editorial team has introduced themed issues, each issue (normally 10-12 papers) will review and explore one or two topical themes from a variety of perspectives. The main theme of the 1997 issue was the evaluation of hypermedia and multimedia systems.

The themes for the 1998 issue of the New Review will be:

- hypermedia for museums and cultural heritage Theme editors Douglas Tudhope and Daniel Cunliffe

- adaptivity and user modeling in hypertext/hypermedia systems: Guest editors Peter Brusilovsky and Maria Milosavljevic (also see Adaptive Hypertext and Hypermedia Home Page http://www.education.uts.edu.au/projects/ah/index.html)

Papers should be submitted to the appropriate theme editors no later than June 1st 1998. For Instructions to Authors, see http://www.comp.glam.ac.uk/~NRHM/ or contact the Editor.

Submissions are welcomed on all aspects of the two themes, including but not restricted to:

Adaptive hypermedia

user modeling in adaptive hypermedia
adaptive educational hypermedia systems
adaptive information systems
adaptive museum hypermedia
adaptive navigation support
natural language techniques for dynamic hypertext generation
adaptive WWW navigation aids
adaptive visualization of hypertext structure
empirical studies of adaptive hypermedia
content adaptation in hypertext and hypermedia
personalized information spaces
adaptivity and adaptability in a hypermedia context
adaptive information retrieval


Guest editors

Peter Brusilovsky - plb (at) cs (dot) cmu (dot) edu

School of Computer Science,

Carnegie Mellon University,

Pittsburgh, PA 15213,

USA.


Maria Milosavljevic - mariam (at) mpce (dot) mq (dot) edu (dot) au

MRI Language Technology Group,

Macquarie University,

Sydney, NSW 2109,

Australia.


Hypermedia for Museums and Cultural heritage

hypermedia link services
networked access
time-varying interactive presentations
image, audio and video databases
navigation design
intelligent hypermedia and agents
web-based museum hypermedia
spatial and temporal models
evaluation and studies of use
metadata and intellectual access
thesauri and semantic representations
copyright /IPR for digital multimedia standards


Editor

Douglas Tudhope - dstudhope (at) glamorgan (dot) ac (dot) uk

Department of Computer Studies

University of Glamorgan

Pontypridd, Mid-Glamorgan CF37 1DL

Wales, UK

fax +1443-482715

tel +1443-482271


Associate Editor (US) Andrew Dillon - adillon (at) ucs (dot) indiana (dot) edu

Associate Editor (UK) Daniel Cunliffe - djcunlif (at) glamorgan (dot) ac (dot) uk


For subscription information, contact

Taylor Graham Publishing, 500 Chesham House,

150 Regent Street, London W1R 5FA, UK.

TOPIC 7:

CFP: Computational Treatment of Portuguese - Brazil [Deadline May 4]

From: lucia (at) dc(dot) ufscar(dot) br (Lucia Rino)


III PROPOR

WORKSHOP ON THE COMPUTATIONAL TREATMENT OF THE

WRITTEN AND SPOKEN PORTUGUESE LANGUAGE


November 3-4, 1998

PUCRS Campus

Porto Alegre - RS

BRAZIL

Sponsored by the Brazilian Computer Society (SBC)

Organized by the Catholic University of Rio Grande do Sul (PUCRS)


CALL FOR PAPERS

Along with the XIV SBIA'98 (Artificial Inteligence Brazilian Symposium), to be held in Porto Alegre, RS, Brazil, in the PUCRS Campus between 04 and 06 of November, 1998, there will be carried out the III PROPOR - III WORKSHOP ON THE COMPUTATIONAL TREATMENT OF THE WRITTEN AND SPOKEN PORTUGUESE LANGUAGE - on the 3rd and 4th of November, 1998.

The former two PROPOR workshops occurred in Portugal and in Brazil, respectively in Feb/1993 and Oct/1996. The third one intends to bring together researchers working on Computational Linguistics, specially those whose work is in any sense related to the processing of the Portuguese language. The main goals of the workshop are to provide the means for the researchers to exchange information and to explore and discuss the availability of resources to solve problems related to Natural Language, having Portuguese as the central language. Contributions should address one or more of the following topics:

  • The automatic interpretation of the Portuguese language
  • The automatic generation of the Portuguese language

  • Verbal discourse processing: problems and resources of the Portuguese language

  • Differences and similarities between the treatment of spoken and written Portuguese

The above topics naturally include a broader discussion on Natural Language Processing as such, and other issues in the Computational Linguistics spectrum. Researchers are invited to submit articles or demoes, in order to integrate, and exchange, experiences with the participants during the event.

Workshop organization

The workshop will consist of technical pannels, conference and discussion sessions. Participants are also invited to present demoes and systems resulting from project and development of software.

Requirements for submission

Papers and software are invited that address any of the topics listed above, preference given to conclusive work. Work reporting ongoing MsC or PhD research can be submitted to the Workshop of Unconcluded Dissertations and Theses, which is held along with SBIA'98. In this case, submission requirements can be found in the following address:

http://www.inf.pucrs.br/~flavio/sbia98/sbia98.html.


IMPORTANT DEADLINES

Technical papers and software descriptions: May 04, 1998 (mailing date)

Notification of acceptance: July 01, 1998 (by email)

=46inal manuscripts due: August 15, 1998 (mailing date)

No electronic submission will be accepted.


INSTRUCTIONS FOR SUBMISSION

Manuscripts must be written either in Portuguese or in English. Please use A4 letter format, doubleline spacing, classical fonts such as Times Roman or Computer Modern, 12 points for text, 14 to 16 points for headings and title. Maximum length is 15 pages including figures and references. Small caps or figures must be avoided, since the manuscripts may be reduced for the proceedings. The content of the first page must include the title of the article, the author(s) fullname(s), institution of origin, address, and a summary of the work. Faxed or emailed work will not be accepted for revision. Software descriptions must contain title, goals and a short characterization, besides the names of the authors, their institution of origin and address, and the specification of software/hardware needs for demoes.

=46our hardcopy copies of both, technical papers or software descriptions, must be accompanied by a letter of submission containing the title of the work, authors, and the name of the contact person. Submissions should be sent to:

Vera L=FAcia Strube de Lima
Instituto de Informatica -PUCRS
Av. Ipiranga, 6681 - Pr=E9dio 16 - Sala 160
CEP 90619-900 Porto Alegre Brasil
E-mail: vera (at) andros(dot)inf(dot)pucrs(dot)br


Organizing committee

Vera L=FAcia Strube de Lima (PUCRS)
Flavio Moreira de Oliveira (PUCRS)
Rosa Maria Viccari (UFRGS)


Program committee

Ariadne M. B. R. Carvalho (IC-UNICAMP)
Clarisse Sieckenius de Souza (DI-PUCRJ)
Elisabete Ranchhod (FL-UL)
Isabel Trancoso (INESC)
Jacques Robin (DI-UFPe)
Jos=E9 Gabriel Pereira Lopes (FCT-UNL)
Laura S. Garcia (CEFET-PR)
L=FAcia Machado Rino (DC-UFSCar)
Mike Dillinger (IL-UFMG)
Raul S. Wazlawick (DI-UFSC)
Rosa Maria Viccari (II-UFRGS)
Vera L=FAcia Strube de Lima(II-PUCRS)


TOPIC 8:

A: KPML Mailing List

From: Elke Teich <elke(at)dude(dot)uni-sb(dot)de>


Announcing the KPML mailing list


KPML (Komet-Penman MultiLingual) is a grammar development environment for Systemic Functional Grammars and a sentence generator for English, German, Dutch and a few other languages. The system was developed at the Institute for Integrated Publication and Information Systems (IPSI) of the German National Research Center for Information Technology (GMD), Darmstadt, Germany (http://www.darmstadt.gmd.de/IPSI/index.html) and is now being further developed at the Center for Language and Communication research at the University of Stirling, UK (http://www.stir.ac.uk/english/communication).

KPML is based on the Penman system for generation of English sentences originally developed at the Information Sciences Institute, University of Southern California.

Added functionalities include

- multilinguality

- facilities for versioning and back-up for large-scale grammar resources

- graphic-based grammar writing tools

- graphic-based grammar exploration tools

- tools for preparing teaching materials

- specialized example and test suite management tools.


KPML has been used in a number of projects and is currently one of the most popular platforms for developing grammars for generation. Users of the system currently develop generation grammars for languages as diverse as English, German, Dutch, French, Spanish, Finnish, Greek, Czech, Russian and Bulgarian. More information about KPML can be found at http://www.stir.ac.uk/english/communication/Computational-tools/ including the requirements for installing the system, downloading the system, documentation etc.

You might also want to have a look at a sample generated document where the text parts are generated with KPML:

http://www.darmstadt.gmd.de/publish/komet/kometpave-pics-96.html


Other relevant pages:

KPML basic:

http://www.stir.ac.uk/english/communication/Computational-tools/kpml.html

KPML documentation (online):

http://www.darmstadt.gmd.de/publish/komet/kpml-1-doc/kpml.html

KPML documentation (downloadable hardcopy):

file://ftp.darmstadt.gmd.de/pub/komet/KPML-1.0/

The Grammar Exploration Tool:

http://www.stir.ac.uk/english/communication/Computational-tools/Grexplorer/grexplorer.html

The generation grammar bank:

http://www.stir.ac.uk/english/communication/Computational-tools/generation-bank.html


This mailing list offers users of KPML the opportunity of exchanging information, seeking and giving advice in issues of linguistic specification and computational implementation, announcing and making available add-on functionalities and new resources etc. The list is managed by the department of English Linguistics, Institute of Applied Linguistics, Translation and Interpreting of the University of the Saarland, Saarbruecken, Germany (http://www.uni-sb.de/~sl16eset/elke.html).


Subscribe NOW and keep in touch!


To subscribe send e-mail to

elke(at)dude(dot)uni-sb(dot)de

by putting 'subscribe MY-E-MAIL-ADDRESS' in the subject field.

TOPIC 9:

P: Diana McKinnie [Generating reports from dictated X-ray reports]

From: Diana McKinnie <LDDMCKIN(at)ihc(dot)com>


I am a PhD student in the Medical Informatics program at the University of Utah. My project deals with generating natural language reports from parsed, dictated X-ray reports. I find the field of natural language generation fascinating and frustrating. I look forward to talking to others with the same fascinations and frustrations.

My e-mail address at the University is: d.mckinnie(at)m(dot)cc(dot)utah(dot)edu.

Thanks- Diana McKinnie


eof

1997

Issue 3

Date: 07 Dec 1997


TOPICS: 1. Q: Evaluation of NL dialogue systems?

2. CFP: COLING-ACL 98 -- Call for Workshop and tutorial proposals -- Deadline: 31 Dec 97

3. CFP: Book -- Advances in Scalable Text Summarization Deadline: 30 Dec 97

4. CFP: ETAI -- Electronic Transactions on AI

5. CFP: TAPD'98 -- Tabulation in Parsing and Deduction Deadline: 12 Dec 97

6. CFP: SIGDAT'98 -- Very Large Corpora Deadline: 20 Apr 98

7. CFP: FOIS'98 -- Formal Ontology in Information Systems Deadline: 15 Dec 97

8. CFP: Discourse Relations and Discourse Markers -- Coling/ACL'98 Deadline: 10 Mar 98

9. CFP: INLG'98 -- International Workshop on NL Generation Deadline: 28 Jan 98

10.JOB: ITRI, Brighton -- Research opportunities

11.JOB: ELRA/ELDA


Topic 1: Q: Evaluation of NL dialogue systems?

From: "gas0" <GAS0(at)elvira(dot)ugr(dot)es>


Ramon Lopez-Cozar Delgado

Electronics and Computer Technology Dept.

University of Granada

18071 Granada, Spain

e-mail: gas0(at)elvira(dot)ugr(dot)es

Fax: +34-58-243230


Dear SIGGEN colleagues:


I am a PhD student and a researcher in the Department of Electronics and Computer Technology at the University of Granada. I am working on a natural language dialogue system that aims to answer product orders and questions of clients in fast-food restaurants. It may be considered a rule-based expert system whose behaviour is decided from a recorded dialogue corpus obtained at a real restaurant. The system is quite developed at the moment, though it needs some improvement to enhance the level of understanding and naturalness.


I would like to get information about the available evaluation methods of such a system, as well as information about the evaluation of natural language dialogue systems in general (used techniques, bibliography, web sites, etc.).


In order to provide more information, I enclose a short abstract about the system I am working on.


--- Abstract ----


The system goal is to simulate the restaurant-clerk behaviour. It must be able to provide information and ask client questions similarly to how a human clerk does. In addition we want it to process spontaneous voiced-speech, which at a linguistic level means to consider phenomena such as unnecessary word repetition, grammatical order change, anaphora, discordances, context information, grammatical mistakes, etc. We also expect a learning ability for the system to allow new information (foods, drinks, ingredients, etc.) acquisition from client interaction.


The basis for the system development is as follows:


- Unnecessary information in client utterance: Usually, not all words in a sentence are necessary to obtain its semantic interpretation, which can be achieved from meaning words only (keywords). To obtain such interpretation, the system uses keywords and a keyword lattice analysis. This analysis is carried out by means of syntactic and semantic rules. From dialogue corpus we found out that clients usually use a small number of words in their utterances (communication client-clerk tends to be telegram-like), therefore a system dictionary can be size-reduced.


- Use of a small number of patterns: Clients tend to communicate using a small number of patterns to order products, ask questions, or modify previous product orders. Using these patterns the system can extract most semantic meanings from clients' utterances. In case the meaning cannot be obtained, clients are asked to help the system understanding process or to repeat the utterance input differently.


The system is a compound of several modules: Input Interface, Control Module, Memory Module, Restaurant-product Knowledge Base, Lexicon, and Output Interface.


At the moment the system takes about 30.000 C++ code lines. Its inputs and outputs are natural language text sentences.


Its Input interface is well developed but still needs to define some syntactic and semantic rules, since now only product orders and questions are carried out.


We are about to start the Modification Module set up. This module will be activated when the desire of modification of previous orders is detected in client input.


Also, the Learning Module needs to be started. This module will be activated when "possible" unknown foods, ingredients, drinks, etc. are detected in client input. These new products will be learnt, so they could be recognized the next time they appear in client sentences.


The Natural Language Generator needs improvement to enhance the expression power, though at the moment, the system can build both syntactically and semantically right sentences, in a very natural fashion, by using pronouns and context information available at the moment of the natural language generation.


The system uses a graphic interface that now is useful but simple. In future we would like to improve it by including product-pictures and graphics of the "artificial" restaurant-clerk face, in order to improve a friendly communication.


We think the integration of the system in a voice-controlled response system represents its best application. To do so, it would need a speech-to-text interface that provides a text-word sequence from client voice. A text-to-speech interface should transform the system output into synthesized voice. Theoretically the whole system could be part of an automatic front-end dialogue system for clients in restaurants, or for those at home who use telephone for ordering.


--- End of Abstract ---


I do not know if this short abstract would be enough for you to get an idea of the system, so in case you need any further information, or in case you have any comment or remark, please let me know.


I look forward to hearing from you soon. Thanks again.


Sincerely,


Ramon Lopez-Cozar Delgado

Electronics and Computer Technology Dept.

University of Granada

18071 Granada

Spain.

Topic 2: CFP: COLING-ACL 98 -- Call for Workshop and tutorial proposals

From: pete(at)sharp(dot)co(dot)uk (Pete Whitelock)


COLING-ACL '98
WORKSHOPS & TUTORIALS
CALL FOR PROPOSALS
University of Montreal
Montreal
Quebec
Canada


The Programme Commitee would like to receive proposals for tutorials and workshops to be held in conjunction with the Joint COLING-ACL Conference.


TUTORIALS


Tutorials will be held on Sunday 9th August, the day preceeding the conference proper. Tutorials may address any topic of current or possible future relevance to the field. The duration of each tutorial should be approximately 3 hours. Those interested in presenting a tutorial should send a 300-500 word proposal to Pete Whitelock, pete(at)sharp(dot)co(dot)uk, describing the relevance of the subject matter to the conference participants, an outline of the tutorial's content, and a short statement of the proposer's relevant experience.


WORKSHOPS


Workshops will be held on Saturday 15th and Sunday 16th of August, immediately following the conference proper. Workshops will normally be one day in length, but may extend to a second day if required. Those interested in organising a workshop should send a brief proposal to Pete Whitelock, pete(at)sharp(dot)co(dot)uk, describing the topic of the workshop and its relevance to Coling, the approximate number of participants expected and the likely duration of the workshop, and a short statement of the proposer's relevant experience.


It is hoped that it will be possible to accomodate all proposals for tutorials and workshops, but the room space available will place an upper limit on the number. Since proposals will be accepted primarily on a first-come first-served basis, proposers are encouraged to submit as early as possible. Early submission is particularly important if workshop presentations are to be refereed. In any event, no proposals will be accepted after the final deadline of Dec 31st.



Topic 3: CFP: Book -- Advances in Scalable Text Summarization

From: Inderjeet Mani <mani(at)azrael(dot)mitre(dot)org>


CALL FOR PAPERS (BOOK)
ADVANCES IN SCALABLE TEXT SUMMARIZATION
Inderjeet Mani and Mark Maybury, editors


With the explosion in the quantity of on-line information in recent years, demand for text summarization technology appears to be growing. Commercial companies are starting to offer text summarization capabilities, often bundled with information retrieval tools. Further, there is considerable interest in mining information from large databases, many of which have text content. These recent developments offer opportunities as well as substantial challenges for research in text summarization. In general, such developments have created a practical need for summarization systems which scale up when applied to large volumes of unrestricted text.


In response to this challenge, a number of new approaches have emerged. Traditionally, shallower techniques have been leveraged to achieve the desired levels of scalability and domain-independence, but recent advances in robust information extraction as well as approaches integrating statistical and symbolic techniques have opened up possibilities for more powerful yet scalable summarization techniques.


With the renewed interest in text summarization, another challenge is to develop rigorous criteria to help evaluate different methodologies, in order to better advise investors and the interested public on technology choices. This state-of-the-art collection will bring together research aimed at advancing the scientific frontiers of text summarization to meet these new practical challenges and opportunities. **The principal aim of this book is to collect some of the key results to date and to identify promising research issues for the benefit of students, corporate researchers, and research program managers interested in learning more about this field.**


Submissions are invited on original research in all aspects of text summarization, including, but not limited to:


TECHNIQUES

* Statistical, linguistic, and knowledge-based techniques in intelligent summarization

* Text summary generation

* Capturing cohesion and coherence relations in text

* Exploiting advances in information extraction in summarization

* Exploiting domain knowledge in scalable text summarization

* Combining scalability with abstraction in summarization

* Tailoring summaries to particular users, tasks, and contexts


NEW PROBLEMS

* Multilingual summarization

* Multimodal summarization

* Multi-document/multi-source summarization


FUNDAMENTAL ISSUES in THEORY AND PRACTICE

* Classification of summarization systems

* Theoretical foundations, including cognitive models

* Evaluation methods and metrics

* Summarization in operational contexts: requirements, architectures, lessons learned


Criteria for selection will include clarity, originality, relevance, and significance of results. The papers will be reviewed by a committee of experts. In addition, authors will be asked to relate the content of their papers to other related papers in the book. In addition to new contributions, the book will also include reprints of classic papers in the field.


Submission Information


DEADLINE FOR SUBMISSION: December 30, 1997

PAPERS REVIEWED BY: March 15, 1997

DRAFT TO PUBLISHERS: July 15, 1997


Interested authors should submit to the address below three copies of a previously unpublished paper no more than 20 pages long, single-spaced, addressing a specific text summarization issue or reporting novel methods and results. Authors should indicate whether the paper is being submitted elsewhere. Please include your name and address on the first page.


For more information, please contact:

Dr. Inderjeet Mani

The MITRE Corporation, W640

11493 Sunset Hills Road

Reston, Virginia 22090, USA

Internet: imani(at)mitre(dot)org

Phone: (703) 883-6149

Fax: (703) 883-1379


Topic 4: CFP: ETAI -- Electronic Transactions on AI

From: Elisabeth Andre <Elisabeth.Andre(at)dfki(dot)de>


*** Call for Papers for the First Issues of the ***
ETAI - ELECTRONIC TRANSACTIONS ON ARTIFICIAL INTELLIGENCE
Organized and published under the auspices of the
European Coordinating Committee for Artificial Intelligence (ECCAI)
http://www.ida.liu.se/ext/etai


AREA: Intelligent User Interfaces

SCOPE:

The ETAI is organized into several specialized areas. The area of Intelligent User Interfaces focuses on design principles, methodologies and tools that make man-machine communication easier and more effective. For ETAI, papers are invited from the whole spectrum of Intelligent User Interfaces research. Topics of interest include, but are not restricted to:


- knowledge-based tools and environments for user interface design and development

- adaptive and customizable user interfaces

- user modeling

- intelligent interface agents and agent-based interaction

- knowledge-based presentation of information

- intelligent interfaces to the internet, for tasks such as design, presentation, access and navigation

- natural-language and multimodal interfaces

- intelligent front-ends to multimedia, hypermedia and virtual environments

- architectures for intelligent user interfaces

- evaluation and analysis of intelligent user interfaces applications, such as tutoring and advisory systems, computer-supported collaborative work, computer-aided design, decision-support systems, information kiosks


CONTRIBUTIONS:


The ETAI welcomes contributions for the first issues of the area: Intelligent User Interfaces. Beside high-quality papers, we seek conference and workshop reports, book reviews and links to software that is available and can be run over the net. Submission guidelines can be found under http://www.ida.liu.se/ext/etai/submission.html For more details contact the area editor (address see below).


AREA EDITOR: Elisabeth Andre, DFKI, Germany


AREA EDITORIAL COMMITTEE (as of September 1997):


Niels Ole Bernsen, Odense University, Denmark

Peter Brusilovsky, CMU, USA

Lynda Hardmann, CWI, NL

James Lester, North Carolina State University, USA

Joe Marks, MERL, USA

Chris Mellish, University of Edinburgh, UK

Ehud Reiter, University of Aberdeen, UK

Constantine Stephanidis, FORTH, Greece

Oliviero Stock, IRST, Italy

Annika Waern, SICS, Sweden


WHAT IS THE ETAI?


The ETAI represents a novel approach to electronic publishing. We do not simply inherit the patterns from the older technology, but instead we have rethought the structure of scientific communication in order to make the best possible use of international computer networks as well as electronic document and database technologies.


Articles submitted to the ETAI are reviewed in a 2-phase process. After submission, an article is open to public online discussion in the area's News Journal. After the discussion period of three months, and after the authors have had a chance to revise it, the article is reviewed for acceptance by the ETAI, using confidential peer review and journal level quality criteria. This second phase is expected to be rather short because of the preceding discussion and possible revision. During the entire reviewing process, the article is already published in a "First Publication Archive", which compares to publication as a departmental tech report.


Compared to mailgroups, the News Journals offer a more persistent and reputable forum of discussion. Discussion contributions are preserved in such a way that they are accessible and referencable for the future. In other words, they also are to be considered as "published".


One additional type of contributions in News Journals is for links to software that is available and can be run over the net. This is particularly valuable for software which can be run directly from a web page.


The creation of bibliographies, finally, is a traditional activity in research, but it is impractical in paper-based media since by their very nature, bibliographies ought to be updated as new articles arrive. The on-line maintenance of specialized bibliographies within each of its topic areas is a natural function in the ETAI.


For more details see: http://www.ida.liu.se/ext/etai/


ADDRESS FOR FURTHER INFORMATION:


Elisabeth Andre

DFKI GmbH

Stuhlsatzenhausweg 3

D-66123 Saarbruecken

Germany

Phone: +49 681 302 5267

Fax: +49 681 302 5341

email: andre(at)dfki(dot)de


Topic 5: CFP: TAPD'98 -- Tabulation in Parsing and Deduction

From: Eric Villemonte de la Clergerie <Eric.Clergerie(at)inria(dot)fr>


TAPD'98
1st Workshop on 'Tabulation in Parsing and Deduction'
April 2-3, 1998
Paris, France
Organized by INRIA
in collaboration with CEDRIC of CNAM
WEB page: http://pauillac.inria.fr/~clerger/tapd.html


MOTIVATIONS


Tabulation techniques are becoming a common way to deal with highly redundant computations occurring, for instance, in Natural Language Processing, Logic Programming, Deductive Databases, or Abstract Interpretation, and related to phenomena such as ambiguity, non-determinism or domain ordering.


Different approaches, including for example Chart Parsing, Magic-Set rewriting, Memoization, and Dynamic Programming, have been proposed whose key idea is to keep traces of computations to achieve computation sharing and loop detection. In addition, tabulation also offers more flexibility to investigate new parsing or proof strategies and to represent ambiguity by shared structures (Shared Proof or Parse Forest).


The first objective of this workshop is to compare and discuss these different approaches. The second objective is to present tabulation and tabular systems to potential users in different application areas. One major area of application is Natural Language Processing, where tabulation has been known for a long time (CKY, Earley, chart parsing). However, sophisticated tabulation techniques are required for the more and more complex grammatical formalisms now used in NLP (unification, constraints, structural complexity). Contributions in other areas, such as picture parsing, genome analysis, or complete deduction techniques, are also encouraged.


TOPICS (not exclusive)

-- Tabulation Techniques:

Chart Parsing, Tabling, Memoization, Dynamic Programming, Magic Set, Generic Fix-Point Algorithms

-- Applications:

Parsing, Generation, Logic Programming, Deductive Databases,Abstract Interpretation, Deduction in Knowledge Bases, Theorem Proving

-- Static Analysis:

Improving tabular evaluation

-- Parsing or resolution strategies.

-- Efficiency issues:

Dealing with large tables (structure sharing, term indexing), Execution models, Exploiting the domain ordering (subsumption).

-- Shared structures (parse or proof forest):

Formal analysis, representation and processing.


WORKSHOP FORMAT: The workshop will be a 2-day event that provides a forum for individual presentations of the accepted contributions as well as group discussions.


SUBMISSION PROCEDURE: Authors are invited to submit before December 12, 1997 a 4-page position paper or abstract concerning a theoretical contribution or a system to be presented. Due to tight time constraints, submissions will be handled exclusively electronically (LaTeX, PostScript, dvi or ascii format). Submissions should include the title, authors' names, affiliations, addresses, and e-mail.


Submissions must be sent to Eric.Clergerie(at)inria(dot)fr


The collection of selected papers will be available at the workshop. After the workshop, authors are invited to submit a full paper for publication in a special issue of the Journal of Logic Programming oriented towards Natural Language Processing. The authors should note that this second submission will be treated according to the standards of the Journal of Logic Programming.


SCHEDULE:

Submission of contributions: 12 December 1997
Notification of acceptance: 26 January 1998
Final versions due: 20 February 1998


PROGRAM COMMITTEE:


Bernard Lang (chairman) -- INRIA, France
Francois Bry -- University of Munich, Germany
Eric de la Clergerie -- INRIA, France
Marc Dymetman -- Xerox, France
Mark Johnson -- Brown University, USA
Baudouin Le Charlier -- University of Namur, Belgium
Mark Jan Nederhof -- University of Groningen, NL
David Rosenblueth -- University of Mexico, Mexico
Manuel Vilares -- University of La Coruna, Spain
David S. Warren -- University of New York at Stony Brook, USA


ORGANIZING COMMITTEE:

Francois Barthelemy -- CNAM, Paris, France
Eric de la Clergerie -- INRIA, Rocquencourt, France
Bernard Lang -- INRIA, Rocquencourt, France
Manuel Vilares -- University of La Coruna, Spain


LOCAL ORGANIZATION:


Claudie Thenault --INRIA, Relations Exterieures, France


ORGANIZATION: Up-to-date information will be available at


http://pauillac.inria.fr/~clerger/tapd.html


For request, please contact:

Eric de la Clergerie
INRIA Rocquencourt Tel: +33 1 39 63 54 10
Domaine de Voluceau - BP 105 Fax: +33 1 39 63 53 30
78153 Le Chesnay Cedex E-mail: Eric.Clergerie(at)inria(dot)fr


Topic 6: CFP: SIGDAT'98 -- Very Large Corpora

From: Eugene Charniak <ec(at)cs(dot)brown(dot)edu>


SIXTH WORKSHOP ON VERY LARGE CORPORA
Preliminary Call for Papers


WHEN: August 15-16, 1998 (immediately following ACL/COLING-98)

WHERE: University of Montreal, Montreal, Quebec, Canada


WORKSHOP DESCRIPTION:


As in past years, the workshop will offer a general forum for new research in corpus-based and statistical natural language processing. Areas of interest include (but are not limited to):


- robust parsing, phrase structure analysis

- part of speech tagging

- term and name identification

- word sense disambiguation

- morphological analysis

- anaphora resolution

- event categorization

- discourse structure identification

- alignment of parallel texts and bilingual terminology

- language modelling

- lexicography

- machine translation

- spelling and grammar correction


PROGRAM CHAIR:


Eugene Charniak Brown University


SPONSOR: SIGDAT (ACL's special interest group for linguistic data and corpus-based approaches to NLP)


FORMAT FOR SUBMISSION:


Only hard-copy submissions will be accepted. Authors should submit six (6) copies of their full-length paper (3500-8000 words) to Eugene Charniak at the Johns Hopkins University address below. Authors should consult the primary call for papers in February for updated specifications.


SCHEDULE:

Submission Deadline: April 20, 1998
Notification Date: June 1, 1998
Camera ready copy due: June 22, 1998


CONTACT:


Eugene Charniak

e-mail ec(at)cs(dot)brown(dot)edu


Address: Before February 1, 1998 and After June 1, 1998

Department of Computer Science

Brown University

Providence RI 02912-1910


Address: From February 1, 1998 until June 1, 1998

Department of Computer Science

Johns Hopkins University

NEB 224, 3400 N. Charles Street

Baltimore, MD 21218-2694


Topic 7: CFP: FOIS'98 -- Formal Ontology in Information Systems

From: Alessandro Artale <artale(at)irst(dot)itc(dot)it>


INTERNATIONAL CONFERENCE ON
FORMAL ONTOLOGY IN INFORMATION SYSTEMS
FOIS'98
In conjunction with
the 6th International Conference on Principles of
Knowledge Representation and Reasoning KR'98


TRENTO, ITALY, JUNE 6-8, 1998


Under the auspices of the Project
ONTOINT
(Ontological Tools for Heterogeneous Knowledge Organization and Integration)
funded by the Italian National Research Council


Research on ontology is becoming increasingly widespread in the computer science community. Its importance has been recognized in fields as diverse as qualitative modelling of physical systems, natural language processing, knowledge engineering, information integration, database design, geographic information science, and intelligent information access. Various workshops addressing the engineering aspects of ontology have been held in the past few years. However, ontology - by its very nature - ought to be a unifying discipline. Insights in this field have potential impacts on the whole area of information systems. In order to provide a solid general foundation for this work, it is therefore important to focus on the common scientific principles and open problems arising from current tools, methodologies, and applications of ontology. The purpose of this conference is to take a first step in this direction.

As the heterogeneity of the program committee indicates, the conference will have a strongly interdisciplinary character. Expected participants include computer science practitioners as well as linguists, logicians, and philosophers. Although the primary focus of the conference is on theoretical issues, methodological proposals as well as papers addressing concrete applications from a well-founded theoretical perspective are welcome.


TOPICS

Examples of problem areas that may be addressed at the conference include:


THEORETICAL ISSUES

* Foundations:

parthood, constitution, identity, integrity, dependence, causality

* Kinds of entity:

particulars vs. universals, continuants vs. occurrents,

abstracta vs. concreta, attributes, relations, qualities,

quantities, tropes or moments, states, situations, environments

* Matter, space, time, motion, change

* Natural kinds, organisms, artifacts

* The ontology of social reality:

legal and administrative entities, artistic expressions

* The ontology of information and information processing:

representations, signs, software products, virtual reality, cyberspace

* Top-level ontological taxonomies:

new proposals or critical analyses of existing ones

* Cognitive foundations of ontological distinctions

* Kinds of ontology:

top-level ontologies, domain ontologies, task ontologies,application ontologies

* Ontological commitment


APPLICATION AREAS

* Knowledge organization, integration and standardization

* Intelligent information access

* Information systems design

* Knowledge engineering

* Conceptual modelling

* Qualitative modelling

* Lexical semantics

* Terminology integration

* Product knowledge integration

* Geographic information systems

* Legal information systems


TOOLS AND METHODOLOGIES

* Ontological and linguistic instruments for conceptual analysis

* Methodologies for ontology development, maintenance, and integration


SUBMISSION OF PAPERS


Papers will be selected on the basis of a rigorous review of full paper contributions. Authors should submit 5 copies to the Conference Chair by December 19, 1997. Papers received after the deadline or not conforming to the submission format will be rejected without review.


Submitted papers must be unpublished and substantially different from papers under review. Papers that have been or will be presented at small workshops/symposia whose proceedings are available only to attendees may be submitted.


Each submission should include a title page containing the title, author(s), affiliation(s), submitting author's mailing address, telephone number, fax number and e-mail address, as well as an abstract and keywords indicating the topic areas listed above that best describe the contribution. Submissions must be at most 16 pages, excluding the title page and the bibliography, with a maximum of 38 lines per page and an average of 75 characters per line (corresponding to the LaTeX article-style, 12pt) using LaTeX or Microsoft Word. Papers should be sent in 5 copies. Fax or electronic submissions will not be accepted.


Those proposing to submit papers must complete the form at the WWW address <http://mnemosyne.itc.it:1024/fois98/> by Monday December 15, 1997. If intending authors do not have WWW access, then an e-mail message must be sent to <fois98(at)irst(dot)itc(dot)it> by the same date, giving details of any proposed submission in the following format:


Title: <Title of paper>

Author: <Last name, initials>

Author: <Insert as many more author lines as necessary>

...

CorrespondingAuthor: <name of corresponding author>

CorrespondingEmail: <email of corresponding author>

CorrespondingAddress: <address of corresponding author>

Keywords: <insert list of keywords, preferably chosen from above list>

Abstract: <insert short abstract, max 200 words>

EndAbstract:


Should intending authors not have e-mail access, the information above should be sent by letter to arrive to the Conference Chair by Monday December 15, 1997.


The proceedings will be published in the IOS-Press (Amsterdam) bookseries 'Frontiers in Artificial Intelligence and Applications' and will be available at the conference. Final camera-ready copies of the accepted papers will be due by March 9, 1998. Authors will be responsible for preparing the final camera-ready in conformity with the formatting requirements laid down by the publisher (see instructions at the FOIS'98 web page http://mnemosyne.itc.it:1024/fois98/submissions.html). Final papers will be allowed at most fourteen (14) pages in the conference proceedings style (corresponding to approximately 20 article-style LaTex pages).


SCHEDULE

Monday, December 15, 1997 Electronic abstracts due
Friday, December 19, 1997 Papers due
Friday, February 6, 1998 Results sent to authors
Monday, March 9, 1998 Final papers due
Saturday-Monday, June 6-8, 1998 FOIS'98


CONFERENCE COMMITTEE


CONFERENCE CHAIR ORGANIZATION CHAIR
Nicola Guarino Alessandro Artale
National Research Council ITC-IRST
LADSEB-CNR Povo, I-38050 Trento, Italy
Corso Stati Uniti, 4 e-mail: artale(at)irst(dot)itc(dot)it
I-35127 Padova, Italy
e-mail: guarino(at)ladseb(dot)pd(dot)cnr(dot)it


ORGANIZING COMMITTEE

Alessandro Artale - Enrico Franconi (ITC-IRST, Trento, Italy)
Nicola Guarino - Claudio Masolo (LADSEB-CNR, Padova, Italy)
Luca Pazzi - Sonia Bergamaschi (Univ. of Modena, Italy)
Geri Steve - Aldo Gangemi (ITBM-CNR, Roma, Italy)
Cristiano Castelfranchi - Rino Falcone (IP-CNR, Roma, Italy)


Topic 8: CFP: Discourse Relations and Discourse Markers -- Coling/ACL'98

From: Eduard Hovy <hovy(at)ISI(dot)EDU>


Coling/ACL 98 workshop
Discourse Relations and Discourse Markers
August 15, 1998
Universite de Montreal
Montreal/Canada


The notion of discourse relation has received many 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:


* What are sound methodologies for comparing similar discourse markers

(contrastive studies, distribution analyses, etc.)?

* What are sound methodologies for relating discourse relations with

potential realizations?

* Are there discourse relations that are *always* lexically signalled?

Are there any that are *never* lexically signalled?

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

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

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

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

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

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

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

* 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?

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

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


Organizing committee


The workshop is organized by

Manfred Stede (Technical University, Berlin)

Leo Wanner (University of Stuttgart)

Eduard Hovy (ISI/USC, Marina del Rey)


This call for papers as well as future information on the workshop can be found at http://www.cs.tu-berlin.de/~marker/aclcolingws.html


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



Topic 9: CFP: INLG'98 -- International Workshop on NL Generation

From: Graeme Hirst <gh(at)cs(dot)toronto(dot)edu>


=============================
9th International Workshop on
NATURAL LANGUAGE GENERATION
5-7 August 1998
Prince of Wales Hotel
Niagara-on-the-Lake, Ontario, Canada


SECOND CALL FOR PAPERS


(For more information, visit http://logos.uwaterloo.ca/~inlg98 )


The 9th biennial Workshop on Natural Language Generation will be held in the scenic town of Niagara-on-the-Lake, near Niagara Falls, in Ontario, Canada, on 5-7 August 1998.


The INLG workshop is the principal gathering for researchers in natural language generation, providing a pleasant atmosphere for stimulating and informative talks on all aspects of the topic. The workshop attracts a healthy mixture of researchers from both universities and research institutes, graduate students, and visitors from related fields such as machine translation, multimedia presentation planning, and parsing. About 65 people are expected to attend the workshop, which traditionally has had a very diverse international representation.


The town of Niagara-on-the-Lake is in the heart of one of Canada's major fruit-growing and wine regions, and is 30 minutes' drive from Niagara Falls. It is one of the oldest settlements in Canada, with many fine examples of Victorian architecture. Niagara-on-the-Lake bills itself as the prettiest town in Canada, and many would agree: its main streets are quaint and picturesque, with many interesting shops, cafes, and restaurants. It is also the home of the Shaw Festival, one of the top North American repertory theatre companies.


The workshop is sponsored by the Association for Computational Linguistics and ACL SIGGEN (Special Interest Group on Natural Language Generation).


The workshop is in the week immediately prior to the joint conference of COLING and ACL, in Montreal, Canada (10-14 August 1998). After the workshop, a bus will take participants who wish to attend COLING / ACL directly to the Toronto train station, for an express train to Montreal (approximately 4 hours).


TOPICS OF INTEREST


Of interest are papers on all topics relating to the automated production of natural language, including but not limited to: discourse structure; grammar; lexis and lexical choice; text planning and schemas (macroplanning); sentence planning (microplanning); semantics and knowledge representation; register, genre, and pragmatics; generator architecture; realization; generator applications; system descriptions; generator evaluation; planning of text formatting; generation in multimedia planning and presentation systems; speech synthesis.


Also welcomed are demonstrations of generation systems, or modules of systems, running either via the Web or on a Sun computer to be provided at the workshop.


REQUIREMENTS FOR SUBMISSION


Papers should describe unique work not published before. They should emphasize the creative and interesting aspects of the work, but should also describe empirical validation and testing as much as possible.


Papers that are being submitted to other conferences must state this fact on the first page.


FORMAT FOR SUBMISSION


Theoretical papers must not exceed 10 pages, including title, references, figures, etc. Please use no smaller than 11pt font, with margins of 1 inch / 2.5 cm all around. Papers not satisfying the specified length and formatting requirements will be rejected without review.


System demonstrations will be reviewed as well. Please send an outline, clearly marked as a system demonstration in the heading, that describes the demonstration, including if possible screen shots. Outlines may not exceed 4 pages, all included, using font no smaller than 11pt and margins of 1 in / 2.5 cm all around. Outlines not satisfying the specified length and formatting requirements will be rejected without review.


ELECTRONIC SUBMISSION


Electronic submissions should be in the form of a PostScript file. This file should be sent to hovy(at)isi(dot)edu, with the subject field "INLG submission".


SUBMISSION IN HARD COPY


Hardcopy submission is possible too. Five copies of the paper or demonstration outline should be sent to:


Eduard Hovy, INLG-98

Information Sciences Institute

4676 Admiralty Way

Marina del Rey, CA 90292-6695

U.S.A.


DEADLINES


Electronic submissions must be received by 28 January 1998, so that they can be printed and checked for completeness. Electronic submissions will be accepted only if they can be printed at ISI.


Hardcopy submissions must be received by 1 February 1998. Late papers will be returned unreviewed.


Notification of receipt will be e-mailed to the first author (or designated author) soon after receipt. Authors will be notified of acceptance before 10 March 1998. Camera-ready copies of final papers prepared in a format to be specified, preferably using a laser printer, must be received by 15 June 1998, along with a signed copyright release statement.


WORKSHOP ORGANIZERS


The workshop is being organized by Chrysanne DiMarco of the University of Waterloo, with the assistance of Graeme Hirst of the University of Toronto. The Program Chair is Eduard Hovy of USC/ISI.


General workshop questions:

Chrysanne DiMarco, cdimarco(at)logos(dot)uwaterloo(dot)ca, phone +1 519 888 4443


General paper-submission questions:

Eduard Hovy, hovy(at)isi(dot)edu, phone +1 310 822 1510 x731


PROGRAM COMMITTEE


Eduard Hovy, USC/ISI, Marina del Rey (chair)

Stephan Busemann, DFKI, Saarbruecken

Susan Haller, University of Wisconsin-Parkside

Helmut Horacek, University of the Saarland

Xiaorong Huang, Formal Systems, Toronto

Kristiina Jokinen, ATR, Kyoto

Guy Lapalme, University of Montreal

Elisabeth Maier, DFKI, Saarbruecken

Chris Mellish, University of Edinburgh

Marie Meteer, BBN

Jon Oberlander, University of Edinburgh

Cecile Paris, CSIRO, Sydney

Owen Rambow, CoGenTex Inc., Ithaca

Ehud Reiter, University of Aberdeen

Elke Teich, Macquarie University, Sydney

Marilyn Walker, AT&T Labs Research, Florham Park


For more information, visit the INLG-98 Website:

http://logos.uwaterloo.ca/~inlg98


Topic 10: JOB: ITRI, Brighton -- Research opportunities

From: Donia Scott <donia.scott(at)itri(dot)bton(dot)ac(dot)uk>

<http://www.itri.bton.ac.uk/posts/summer97.html>


ITRI, University of Brighton


The Information Technology Research Institute (ITRI) at the University of Brighton, is a major centre for research in Computational Linguistics and Language Engineering. Our principal research areas are natural language generation, lexicons, corpora and human computer interfaces. Our current research programme addresses the following theoretical issues: anaphora, architectures for natural language generation, automated interface design, constraint based reasoning, controlled languages, corpora, diagrammatic reasoning, discourse, document design, integrating text and graphics, lexical knowledge bases, lexical representation, multilinguality, natural language interfaces, text generation, underspecification, word sense disambiguation.


The Institute is comprised of around twenty staff and students: research professors, readers, research fellows, research assistants, postgraduate students and technical and administrative staff. We also regularly host visiting researchers from other universities worldwide.


The Institute is housed in a self-contained brand new office suite with excellent computing and network facilities and full administrative support. As a dedicated research department, we place great emphasis on career management and development, and participation in the wider research community.


We are currently recruiting to fill up to six fixed-term research posts over the next few months, ranging from research officers to principal research fellows for up to three or five years in duration. A number of PhD studentships may also be available.


If you are interested in working with us, we would be interested in hearing from you. Please address all enquiries, enclosing a CV if possible, to the address below. Suitable potential candidates will be sent further information. Meanwhile, more detailed information regarding the Institute is available on our web site.


Ms Vivienne Wicks, Research Administrator, Information Technology Research Institute, University of Brighton, Lewes Road, Brighton, BN2 4GJ, United Kingdom.


Tel: +44 1273 642900 Email: admin(at)itri(dot)brighton(dot)ac(dot)uk
Fax: +44 1273 642908 URL: http://www.itri.brighton.ac.uk/


Topic 11: JOB: ELRA/ELDA

From: elra-elda(at)calva(dot)net (Malin Nilsson)

===============================================

TECHNICAL ASSISTANT at ELRA/ELDA in Paris

===============================================


ELRA, the European Language Resources Association, has an immediate vacancy for a Technical assistant for ELDA, its Paris-based distribution agency. ELRA, a non-profit association registered in Luxembourg, was established in 1995 and receives financial support from the European Commission and national governments to promote the development and exploitation of Language Resources - monolingual and multilingual lexica, text corpora, speech databases and terminology - in Europe. Enjoying strong backing from the language engineering industry, ELRA's operations are conducted by the CEO and his team at ELDA.


The role of the new technical assistant will be to contribute to the work of a small support team in the development of the infrastructure for the collection, validation, and licensing of LR and in the interactions with the relevant players (i.e. producers, owners and users of LR who may be in the industrial, commercial or academic world; and governmental and non-governmental agencies), with a particular focus on textual and terminological resources.


This position yields excellent opportunities for young, creative, and motivated candidates wishing to participate actively in establishing/building the European Union Language Engineering field. Terms and conditions of employment are subject to negotiation, but will be commensurated with the responsibilities of the post and will include performance-based incentives. ELRA will pay relocation expenses for the selected candidate. This is initially a one-year appointment with a strong possibility of a further two years or permanent employment.


Qualifications:

- Excellent track record in Language Engineering and related fields.

- Technical experience in design and development of Language Engineering

solutions (preference for candidats with experience in the fields of written

text and/or terminology).

- Experience in collecting, validating, and marketing language resources,

software or other forms of intellectual property. =09

- Experience in packaging language resources for distribution using=

CD-ROM,

ftp facilities, etc.. will be a plus.

- Citizenship of, or residency papers for an EU country.

- Ability to work in at least two European languages including English.


Applicants should send a cover letter addressing the points listed above, together with a current Curriculum Vitae, to: ELRA Distribution Agency (ELDA), Dr. Khalid Choukri, 87, Avenue d'Italie F-75013 Paris, France Fax +33 1 45 86 44 88; e-mail: elra(at)calvanet(dot)calvacom(dot)fr For more information on ELRA, see:http://www.icp.grenet.fr/ELRA/home.html (English) or /ELRA/fr/home.html (French) Initial applications by e-mail will be accepted with follow-up by post/fax.


eof


Issue 2

=============================
9th International Workshop on
NATURAL LANGUAGE GENERATION


5-7 August 1998


Prince of Wales Hotel
Niagara-on-the-Lake, Ontario, Canada


CALL FOR PAPERS


(For more information, visit http://logos.uwaterloo.ca/~inlg98 )


The 9th biennial Workshop on Natural Language Generation will be held in the scenic town of Niagara-on-the-Lake, near Niagara Falls, in Ontario, Canada, on 5-7 August 1998.


The INLG workshop is the principal gathering for researchers in natural language generation, providing a pleasant atmosphere for stimulating and informative talks on all aspects of the topic. The workshop attracts a healthy mixture of researchers from both universities and research institutes, graduate students, and visitors from related fields such as machine translation, multimedia presentation planning, and parsing. About 65 people are expected to attend the workshop, which traditionally has had a very diverse international representation.


The town of Niagara-on-the-Lake is in the heart of one of Canada's major fruit-growing and wine regions, and is 30 minutes' drive from Niagara Falls. It is one of the oldest settlements in Canada, with many fine examples of Victorian architecture. Niagara-on-the-Lake bills itself as the prettiest town in Canada, and many would agree: its main streets are quaint and picturesque, with many interesting shops, cafes, and restaurants. It is also the home of the Shaw Festival, one of the top North American repertory theatre companies.


The workshop is sponsored by the Association for Computational Linguistics and ACL SIGGEN (Special Interest Group on Natural Language Generation).


The workshop is in the week immediately prior to the joint conference of COLING and ACL, in Montreal, Canada (10-14 August 1998). After the workshop, a bus will take participants who wish to attend COLING / ACL directly to the Toronto train station, for an express train to Montreal (approximately 4 hours).


TOPICS OF INTEREST


Of interest are papers on all topics relating to the automated production of natural language, including but not limited to: discourse structure; grammar; lexis and lexical choice; text planning and schemas (macroplanning); sentence planning (microplanning); semantics and knowledge representation; register, genre, and pragmatics; generator architecture; realization; generator applications; system descriptions; generator evaluation; planning of text formatting; generation in multimedia planning and presentation systems; speech synthesis.


Also welcomed are demonstrations of generation systems, or modules of systems, running either via the Web or on a Sun computer to be provided at the workshop.


REQUIREMENTS FOR SUBMISSION


Papers should describe unique work not published before. They should emphasize the creative and interesting aspects of the work, but should also describe empirical validation and testing as much as possible.


Papers that are being submitted to other conferences must state this fact on the first page.


FORMAT FOR SUBMISSION


Theoretical papers must not exceed 10 pages, including title, references, figures, etc. Please use no smaller than 11pt font, with margins of 1 inch / 2.5 cm all around. Papers not satisfying the specified length and formatting requirements will be rejected without review.


System demonstrations will be reviewed as well. Please send an outline, clearly marked as a system demonstration in the heading, that describes the demonstration, including if possible screen shots. Outlines may not exceed 4 pages, all included, using font no smaller than 11pt and margins of 1 in / 2.5 cm all around. Outlines not satisfying the specified length and formatting requirements will be rejected without review.


ELECTRONIC SUBMISSION


Electronic submissions should be in the form of a PostScript file. This file should be sent to hovy@isi.edu, with the subject field "INLG submission".


SUBMISSION IN HARD COPY


Hardcopy submission is possible too. Five copies of the paper or demonstration outline should be sent to:


Eduard Hovy, INLG-98

Information Sciences Institute

4676 Admiralty Way

Marina del Rey, CA 90292-6695

U.S.A.


DEADLINES


Electronic submissions must be received by 28 January 1998, so that they can be printed and checked for completeness. Electronic submissions will be accepted only if they can be printed at ISI.


Hardcopy submissions must be received by 1 February 1998. Late papers will be returned unreviewed.


Notification of receipt will be e-mailed to the first author (or designated author) soon after receipt. Authors will be notified of acceptance before 10 March 1998. Camera-ready copies of final papers prepared in a format to be specified, preferably using a laser printer, must be received by 15 June 1998, along with a signed copyright release statement.


WORKSHOP ORGANIZERS


The workshop is being organized by Chrysanne DiMarco of the University of Waterloo, with the assistance of Graeme Hirst of the University of Toronto. The Program Chair is Eduard Hovy of USC/ISI.


General workshop questions:

Chrysanne DiMarco, cdimarco@logos.uwaterloo.ca, phone +1 519 888 4443


General paper-submission questions:

Eduard Hovy, hovy@isi.edu, phone +1 310 822 1510 x731


PROGRAM COMMITTEE


Eduard Hovy, USC/ISI, Marina del Rey (chair)

Stephan Busemann, DFKI, Saarbruecken

Susan Haller, University of Wisconsin-Parkside

Helmut Horacek, University of the Saarland

Xiaorong Huang, Formal Systems, Toronto

Kristiina Jokinen, ATR, Kyoto

Guy Lapalme, University of Montreal

Elisabeth Maier, DFKI, Saarbruecken

Chris Mellish, University of Edinburgh

Marie Meteer, BBN

Jon Oberlander, University of Edinburgh

Cecile Paris, CSIRO, Sydney

Owen Rambow, CoGenTex Inc., Ithaca

Ehud Reiter, University of Aberdeen

Elke Teich, Macquarie University, Sydney

Marilyn Walker, AT&T Labs Research, Florham Park


For more information, visit the INLG-98 Website:

http://logos.uwaterloo.ca/~inlg98

Issue 1

Date: 2 Jan 1997



TOPICS:

1. NEW! SIGGEN WEB SITE <http://www.cs.bgu.ac.il/siggen>

2. Contribute: workshop papers, thesis, siggen directory.

3. ELRA News

4. CFP: RIAO'97 Computer Assisted Information Searching On Internet

25 June 97, Montreal - Deadline March 3, 1997

<mailto:Abdellatif.Saoudi(at)irin(dot)univ-nantes(dot)fr>

5. NLP Research Positions in Sydney, Australia <rdale(at)mpce(dot)mq(dot)edu(dot)au>

6. CFP: EMNLP-2 (SIGDAT) - Deadline: March 3, 1997

August 1-2, 1997 (Immediately following AAAI-97) - Brown University

7. CFP: EUROSPEECH 97 - Deadline: 1 February 1997

Rhodes, Greece, 22-25 September 1997

8. CFP: BISFAI'97 - Deadline: February 2nd 1997


June 16-18, 1997, Bar-Ilan University, Ramat-Gan, Israel




Topic 1:

From: siggen(at)cs(dot)bgu(dot)ac(dot)il (Michael Elhadad)

Subject: SIGGEN Web site

Happy new year! SIGGEN is finally moving to the era of the World Wide Web.

The SIGGEN Web site is:

<http://www.cs.bgu.ac.il/siggen>


Please check it and contribute material to add there. Send me all your

comments. I have been thinking about adding a members directory. I believe

the best way is if you want to have your name and http address added there with

a short description of your interests, please mail them to me and I will

maintain the directory (until someone contributes a program to do these things

automatically).


From now on, I will add conference and workshop announcements on the Web site

and only send pointers in the newsletter (which will become much shorter).


With the new year, feel free again to contribute to this newsletter: send

questions, update on your research, paper announcements, reaction on published

papers, reviews etc.


The newsletter is sent approximately every two months. If you want to remove

your name from the list, please send email to siggen(at)cs(dot)bgu(dot)ac(dot)il.


Topic 2:

From: siggen(at)cs(dot)bgu(dot)ac(dot)il (Michael Elhadad)

Subject: Previous workshop papers


Many people have observed that many Generation papers have appeared in one of

the previous Workshops on Generation. These papers are difficult to find. We

should make every effort to make them more available. This is a call to all

authors of papers previously published in one of the Generation Workshops to

send to SIGGEN a pointer to the file(s) of the paper.


The SIGGEN Web site also contains pointers to generation resources: papers,

thesis, software. Contribute!



Topic 3:


From: elra(at)calvanet(dot)calvacom(dot)fr (Khalid Choukri)

Subject: INFORMATION FROM ELRA (European Language Resources Association)


INFORMATION FROM THE
European Language Resources Association


ELRA News


ELRA (European Language Resources Association), was founded in Luxembourg in

February 1995, as a non-profit organization, with the goal of promoting the

creation, verification and distribution of Language Resources (LR). In addition

to helping users and developers, government agencies, and other interested

parties exploit language resources for a wide variety of use, ELRA serves as

the European repository for EU-funded language resources, and interact with

similar bodies in other parts of the world. Funded in the medium term by

membership fees, grants from the European Commission and national governments,

together with projects income, the Association will be financially

self-supporting in the long run. A 12-member Board is in charge of the strategy

and objectives to be adopted by the Association.


Relevant LR are Spoken Databases, Lexica, Grammars, Written Corpora and

Terminological Data. These are required for the development of speech and text

processing systems for a large number of applications in various information

technology areas.


ELRA licences LR for R&D, as soon as these are made available. According to the

agreements made between ELRA and its providers, resources can be either

reserved for research purposes or used for the development of products and

services. Licence agreements, drawn with the support of lawyers, are used for

negotiations. Such contracts are available at ELRA office. Lexica, Corpora

(spoken and written), Grammars and Tools are described in easy-to-understand

presentation forms. All these documents can be found on the ELRA Web site.


ELRA Newsletters


A Newsletter is released by ELRA every Quarter. The next three issues will

primarily and alternatively be devoted to each of the 3 Colleges of the

Association : spoken, written and terminological resources. The October

Newletter (vol.1 n.3) is already available at ELRA office. It is entirely

dedicated to Terminology. The next two issues will be dedicated to written and

spoken resources.

The ELRA Web site


The ELRA Web site is now available in English and French. The URL addresses are: English version: <http://www.icp.grenet.fr/ELRA/home.html>

French version : <http://www.icp.grenet.fr/ELRA/fr/home.html>


ELRA Language Resources catalogue


A catalogue of the LR negotiated or under negotiation by ELRA can be found on

our Web site. For quotation, please refer to this site or directly to ELRA

office. A published version is released twice a year (together with number 1

and 3 of the Newsletter).


Resources appearing in the catalogue are separated according to the three

Colleges : spoken resources, written resources (corpora, lexica and tools) and

terminological resources. The catalogue consists of :


1) Spoken resources : 30 databases (recordings from microphone, telephone,

continuous speech, isolated words, several languages, etc.).


2) Written resources :

* 9 monolingual and multilingual corpora

* 12 monolingual lexica

* Over 30 multilingual lexical

* A linguistic software platform and Grammars Development platform


3) Terminological resources : over 90 databases with a wide range of domains

and several languages (French, English, German, Spanish, Danish, Italian,

Catalan, Turkish, Polish, Portuguese).


ELRA Membership


ELRA members are entitled to substantial discounts on public prices of the

resources and other products (such as the Guide for Terminology Agreements and

several commercial reports).


ELRA membership is open to any organization, public or private, with full

membership (including voting privileges) being available to organizations

registered in Europe. Purely for organizational purposes, members will be

assigned to one of the Colleges on the basis of their main area of

interest. The annual membership fee has been set at a modest ECU 1,000 to

encourage broad participation. You may also opt to join more than one College,

in which case you will be required to pay multiple membership fees.


Please ask for a membership form or download it from the ELRA Web site.


For further information :

ELRA/ELDA
87, Avenue d'Italie
FR-75013 PARIS
FRANCE


Tel : +33 01 45 86 53 00
Fax : +33 01 45 86 44 88
E-mail : elra(at)calva(dot)net
http://www.icp.grenet.fr/ELRA/home.html


Topic 4:

From: Abdellatif.Saoudi(at)irin(dot)univ-nantes(dot)fr (Abdellatif Saoudi)


CALL FOR PAPERS
5TH RIAO CONFERENCE
COMPUTER ASSISTED INFORMATION SEARCHING ON INTERNET


25th-27th June 1997
McGill University, Montreal, Quebec H3A 2T7,Canada,


"RIAO 97" will be the fifth conference in the series. RIAO 85 took place in

France, RIAO 88 at MIT (Cambridge MA., U.S.A.), RIAO 91 in Barcelona, Spain,

and RIAO 94 in New York. The Conference is organized by the "CENTRE DE HAUTES

ETUDES INTERNATIONALES D'INFORMATIQUE DOCUMENTAIRE" (CID) Paris.


Facing the growth of document information available throught the Internet way

(Web sites, NewsGroups or emails), it is necessary to offer new technologies,

mechanisms and systems to manage all that information. The huge amount of

information implies rapid indexing and retrieval engines, efficient datamining

and knowledge discovery systems in oder to find relevant or strategic

information. On one hand,linguistic tools are necessary when managing textual

information ; one the other hand specifics problems have to be solved regarding

the management of multimedia information : multimedia information

characterisation, search mechanisms, multimedia interfaces. Tools are also

necessary to deal with the diversity of the information source. Where is the

relevant information stored? Which are the best sources? How can heterogeneous

repositories be queried, ...? Finally, the current ways of diffusing

information such as the Internet lead to security problems that must not be

overlooked.


The purpose of this conference is to confront specialists in media contents

with specialists in Web-based searching.


More specifically, papers are expected to cover one or more of the following

topics :

A - Rapid indexing and retrieval engines, automatic abstracting

B - Evaluation of linguistic tools in information retrieval

C - Information Retrieval from several repositories

- Identification of duplicated documents in different

repositories (different languages, structures or versions),

- Unification of documents from heterogeneous repositories ;

datawarehousing,

- Interest of the use of datamining and knowledge discovery

strategies when querying large repositories,

- Evaluation of repository for a given search strategy.

D - Technology watch techniques using strategy on the Web ;

content adressable electronic mail, news group, WWW systems.

E - Architecture

- How can large data flows be exploited by information retrieval tools,

- Distributed, multi-agent architectures

F - Image

- Image content characterisation, human and automatic image description methods,

- Image search strategies

G - Sound

- Sound content characterisation,

- Automatic identification of sound type: speech, music...,

- Spoken language recognition,

- Word-spotting.

H - Content-based compression techniques

I - Multimedia interfaces : Iconic, navigational, speech interface

to web search

J - Data security problems: copyright protection, internet crime

K - Web-related international conventions and policies


IMPORTANT DATES :

Closing date for submission: 20 January 1997
Notification of acceptance: 10 March 1997
Camera-ready copy: 10 May 1997
Conference start-date: 25 June 1997

Detailed information regarding RIAO-97 can be found on the World Wide

Web Server :

http://www.sciences.univ-nantes.fr/RIAO97/



Topic 5:

From: Robert Dale <rdale(at)mpce(dot)mq(dot)edu(dot)au>

Subject: NLP Research Positions in Sydney, Australia


Are you in the northern hemisphere? Chilly, huh? Well: why not carry

out research in language technology in Sydney, Australia ...


The Microsoft Research Institute's Language Technology Group, situated

on the campus of Macquarie University in Sydney, is currently seeking

to hire two research scientists. The successful candidates will work

on a number of ongoing and new projects in the areas of natural

language processing and language engineering. We are particularly

interested in hiring people to work in the following three areas:


automatic text generation;

intelligent text processing and information extraction; and

connecting language and action.


Generally, we expect research staff to spend approximately 50% of

their time working on group projects, and 50% pursuing other research

avenues of their own devising. We are particularly interested in

candidates with previous experience in one or more of the following

areas:


corpus-based and statistical methods;

message extraction and understanding;

the use of natural language processing techniques in information

retrieval;

the design and development of dialogue systems;

text planning; and

linguistic realisation.


Applicants should have a postgraduate degree in computational

linguistics, computer science or linguistics, and competence in

several areas drawn from the following portfolio:


Computational linguistic theory: a basic understanding of parsing

techniques; a grounding in one or more syntactic theories; a

familiarity with techniques in statistical text processing; an

understanding of issues in discourse processing; an awareness

of the breadth of issues in the field; and

The ability to program (well!) in one or more of: C, C++, or Lisp.


MRI offers excellent computational facilities and the opportunity to

work in an expanding team that carries out leading-edge research in

language technology. MRI is located on the campus of Macquarie

University in North Ryde, a suburb of Sydney, Australia, one of the

world's most beautiful cities.


The positions will become available from January 1997, although actual

start dates are negotiable. The positions are open to those

considering postdoctoral positions as well as more experienced

candidates. Please send your application (including a CV and list of

publications) by email to Robert Dale (Robert.Dale(at)mq(dot)edu(dot)au) as soon

as possible and by January 1st 1997 at latest. Early indications of

interest would be useful if received by December 13th 1996. Informal

enquiries can be sent to the same address.


Find out more about MRI at <http://www.mri.mq.edu.au/ltg/>



Topic 6:

From: yarowsky(at)blaze(dot)cs(dot)jhu(dot)edu (David Yarowsky)

Subject: Call for Papers - EMNLP-2


The Association for Computational Linguistics and its

Special Interest Group SIGDAT announce the

Second Conference on
Empirical Methods in Natural Language Processing
(EMNLP-2)


Preliminary Call For Papers


WHEN: August 1-2, 1997 (Immediately following AAAI-97)

WHERE: Brown University, Providence, Rhode Island, USA


CONFERENCE DESCRIPTION:

In the spirit of SIGDAT events, this conference will offer a general

forum for novel research in corpus-based and statistical natural

language processing. Areas of interest include (but are not limited

to):

- robust parsing, phrase structure analysis

- part of speech tagging

- term and name identification

- word sense disambiguation

- morphological analysis

- anaphora resolution

- event categorization

- discourse structure identification

- alignment of parallel texts and bilingual terminology

- language modelling

- lexicography

- machine translation

- spelling and grammar correction


SPECIAL SESSIONS: INFORMATION EXTRACTION and INFORMATION RETRIEVAL


In addition, we encourage submissions that describe and evaluate the

strengths, weaknesses, and recent advances in corpus-based NLP as

applied to INFORMATION EXTRACTION and INFORMATION RETRIEVAL (IR).


In recent years a number of corpus-based techniques for the automatic

linguistic annotation of text have been developed. How well do these

techniques for lexical tagging, parsing, anaphora resolution, etc.,

handle the specific problems encountered in practical language

processing tasks like information extraction and information

retrieval? When and how do current techniques fail? What new methods

have been developed to address the deficiencies of existing algorithms

for these tasks or to address problems specific to information

extraction? What problems still lack an adequate empirical solution?

How can data-driven NLP methods be used to improve the performance of

IR systems? Conversely, how can feedback from an IR system

effectively inform empirical techniques for natural language

understanding?


PROGRAM CHAIRS:

Claire Cardie Cornell University (chair)
Ralph Weischedel BBN Systems and Technologies (co-chair)


LOCAL ARRANGEMENTS:

Eugene Charniak Brown University

SPONSOR: SIGDAT (ACL's special interest group for linguistic data and corpus-based approaches to NLP)


FORMAT FOR SUBMISSION: Authors should submit a full-length paper

(3500-8000 words) either electronically or in hardcopy. Electronic

submissions should be mailed to "cardie(at)cs(dot)cornell(dot)edu" and must

either be (a) plain ascii text, (b) a single postscript file (US

letter format), or (c) a LaTex file. In the latter case, please use

the aclsub style file and include only .EPS (encapsulated postscript)

figures. The aclsub style file is available at

http://www.cs.cornell.edu/Info/People/cardie/emnlp/aclsub.sty or via

ftp from ftp.cs.cornell.edu/pub/cardie/emnlp/aclsub.sty. Hardcopy

submissions should be mailed to Claire Cardie (address below), and

should include six (6) copies of the paper.


REQUIREMENTS: Papers should describe original work. A paper accepted

for presentation cannot be presented or have been presented at any

other meeting. Papers submitted to other conferences will be

considered, as long as this fact is clearly indicated in the

submission.

SCHEDULE:

Submission deadline: March 3, 1997
Notification date: April 21, 1997
Camera-ready copy due: June 10, 1997
Conference dates: August 1-2, 1997


CONTACTS:

Claire Cardie Ralph Weischedel
Cornell University BBN Systems and Technologies
Department of Computer Science 70 Fawcett Street
4142 Upson Hall Cambridge, MA 02138
Ithaca, NY 14850 USA USA
cardie(at)cs(dot)cornell(dot)edu weischedel(at)bbn(dot)com
(607)255-9206 (617)873-3496


Topic 7: From m.scordilis(at)wcl(dot)ee(dot)upatras(dot)gr Mon Dec 23 17:46:27 1996

Subject: EUROSPEECH'97 FINAL CALL FOR PAPERS


European Speech Communication Association
(ESCA)


EUROSPEECH'97


5th EUROPEAN CONFERENCE20
ON SPEECH COMMUNICATION AND TECHNOLOGY


RHODES, GREECE
22-25 SEPTEMBER 1997


FINAL CALL FOR PAPERS


AIMS

The Fifth biennial European Conference on Speech Communication and Technology,

EUROSPEECH'97, of the European Speech Communication Association (ESCA), will be

held on the island of Rhodes, Greece, organized by the University of Patras,

Wire Communications Laboratory. Rhodes is situated in the southern Aegean Sea,

in the Mediterranean and it is famous for its natural beauty, its archeological

treasures and its highly developed tourism. ESCA is the European organization

that promotes research, development and applications in SPEECH COMMUNICATION

AND TECHNOLOGY. Host cities of the previous conferences were Paris (1989),

Genova (1991), Berlin (1993) and Madrid (1995). The upcoming conference will

include the latest developments in this field of major international

importance, presented in oral and poster sessions . Furthermore it will

include several keynote addresses by distinguished scientists. All

presentations and printed material will be in English, which is the official

language of the conference. In addition to the technical program, an exhibition

of products, services and prototypes related to Speech and Language

Communication and Technology will be held during the conference. Prospective

authors are invited to propose papers in any of the listed technical areas.

TECHNICAL AREAS


A. Speech production and perception

B. Phonetics and phonology

C. Prosody

D. Neurophysiology, psychoacoustics and psycholinguistics of speech

E. Auditory modeling

F. Speech analysis and modeling

G. Neural networks for speech and language processing

H. Robust speech processing, signal enhancement and noise reduction

I. Text-to-speech synthesis

J. Speech and audio coding and transmission

K. Speech recognition and understanding

L. Language modeling

M. Spoken dialogue systems design

N. Speaker and language recognition

O. Spoken language resources, assessment, standards and human factors

P. Multimodal speech and language processing20

Q. Technology for speech and language acquisition and learning

R. Applications for speech, language and hearing disorders and aids for

the communication impaired

S. Speech and language engineering for the telecommunications

T. Systems, hardware and architectures for speech processing

U. Applications of speech technology

V. Other related areas or emerging techniques and applications


SUBMISSION OF ABSTRACTS

Abstracts of original, not elsewhere published papers may be submitted either

by post (four copies must be submitted) or by e-mail in postcript or ascii

format only. They must be received no later than 1 February 1997 together with

the completed EUROSPEECH'97 Abstracts Cover Form given below. Abstracts should

not exceed two A4 pages (including figures and references). All submissions

will be acknowledged. E-mail abstracts will be acknowledged within 24 hours. If

they are not acknowledged, please check the e-mail address and resubmit. All

abstracts will be refereed by the Scientific Programme Committee. Submission of

an abstract implies a commitment to present the paper if accepted.

ABSTRACTS SUBMISSION ADDRESS:

EUROSPEECH'97

Wire Communications Laboratory

Department of Electrical and Computer Engineering

University of Patras

26110 Rion, Patras, GREECE

E-mail: Abstracts-EURO97(at)wcl(dot)ee(dot)upatras(dot)gr


SPECIAL SESSIONS


EUROSPEECH'97 will include a Special Session on "Education for Language &

Speech Communication Sciences", which aims to address educational issues of

Phonetics, Spoken Language Engineering, Speech and Language Therapy, Computer

assisted learning (CAL) and the use of internet. Abstracts submitted for this

session must be indicated in the space provided in the Abstracts Cover

Form. For more information please contact:

Gerrit Bloothooft 20

Research Institute for Language and Speech (OTS)

Trans 10, 3512 JK Utrecht, The Netherlands

Phone: +31.30.2536042

Fax: +31.30.2536000

Email: Gerrit.Bloothooft(at)let(dot)ruu(dot)nl


SCHEDULE


Submission of abstracts To be received by 1 February 1997
Notification of acceptance To be mailed out by 1 April 1997
Submission of photo-ready papers To be received by 20 May 1997


SATELLITE EVENTS


ESCA WORKSHOP ON INTONATION, 18-20 September 1997, at Athens, Greece.

Information contact: Antonis Botinis

Tel: +30 1 7211119

Fax: +30 1 7228981

E-mail: tonesca(at)di(dot)uoa(dot)gr

WWW server: http://www.di.uoa.gr/esca


EU SPEECH PROJECTS DAY, Monday, 22 September 1997, 9:00-13:00,

Convention Centre, Rodos Palace Hotel, Rhodes, Greece.

Information contact: Giovanni Battista Varile

European Commission, DG XIII E5 - Language Engineering

Tel: +352 430 132 867 Fax: +352 430 134 999 E-mail: Giovanni.Varile(at)lux(dot)dg13(dot)cec(dot)be


COCOSDA WORKSHOP'97 (The International Coordinating Committee for Speech

Databases and Speech I/O Systems Assessment), Friday, 26 September 1997,

9:00-13:00, Convention Centre, Rodos Palace Hotel.

Information contact: Mark Liberman

University of Pennsylvania

Tel: +1 215 898 0464 Fax: +1 215 573 2175

E-mail: myl(at)unagi(dot)cis(dot)upenn(dot)edu


European Tutorial & Research Workshop on AUDIO-VISUAL SPEECH PROCESSING:

Computational & Cognitive Science Approaches, 27-28 September 1997,

Centre, Rodos Palace Hotel, Rhodes (Greece).

Information contact: Christian BENOIT

Institut de la Communication Parlee, UPRESA CNRS No 5009, Universite

Stendhal,20

BP 25 X, F38040 Grenoble Cedex 9, FRANCE

Tel: (+33).4.76.82.43.36 Fax: (+33).4.76.82.43.35

E-mail: benoit(at)icp(dot)grenet(dot)fr

Web page: http://ophale.icp.grenet.fr/


COST WORKSHOP (Cooperation in the field of Scientific and Technical

research), 26-27 September 1997, Athens, Greece. Information contacts:

COST 249 COST 250

Continuous Speech Recognition Speaker Recognition in Telephony

Jean Pierre Martens Andrea Paoloni
Tel: +32 91 264 3395 Tel: +39 6 5480 3351
Fax: +32 91 264 3594 Fax: +39 6 5480 4405
E-mail: martens(at)elis(dot)rug(dot)ac(dot)be E-mail: pao(at)fub(dot)it


WEB-SITE

The Call for Papers, Call for Exhibitors and Sponsors, all necessary

forms, and continuously updated information about the Conference, as

well as about Greece and Rhodes, can be found at our web site at:

<http://www.cti.gr/~ee-www/>



Topic 8:

From: Leo Joskowicz <josko(at)cs(dot)huji(dot)ac(dot)il>

Subject: BISFAI'97


****** Call for Papers ******
BISFAI '97


The Fifth Bar-Ilan Symposium on
Foundations of Artificial Intelligence


June 16-18, 1997
Bar-Ilan University, Ramat-Gan, Israel


in cooperation with


Israel Association for Artificial Intelligence
Israeli Society for Theoretical Computer Science
Gelbart Institute for Mathematical Sciences
The Association for Mathematics of Language
The Leibniz Center for Research in Computer Science


The focus of BISFAI '97 will be on Intelligent Agents. The Symposium will,

however, retain its broad scope, and welcomes high quality research papers

in various areas of Artificial Intelligence, including machine learning,

automated reasoning, knowledge representation, neural nets, natural

language processing, etc.


The concept of an agent has become important in both artificial

intelligence and mainstream computer science. An agent is a hardware or

software system that is automonous, interactive with and reactive to its

environment and other agents. An agent can also be pro-active in taking the

initiative in goal-directed behaviour.


We solicit papers in all areas of Artificial Intelligence, and in

particular in the area of Intelligent Agents. Agents have a clear and

growing importance, both practical and theoretical. Because of their

commercial relevance, we encourage practitioners from industry to submit

papers dealing with various practical aspects.


Distinguished Invited Speakers (tentative):

C. Boutilier (U. of British Columbia)
V. Lesser (U. of Massachusetts)
J. Rosenschein (Hebrew U.)
G. Shafer (Rutgers U.)
Y. Shoham (Stanford U.)
P. Struss (Technical University of Munich)
W. Wahlster (DFKI GmbH)


THE 1997 ISRAELI FEDERATED COMPUTING CONFERENCE: The Symposium will be part

of the new Israeli Federated Computing Conference (IFCC). For contact

points on this conference, see below). The IFCC will also include the

Eighth Israeli Conference on Computer-Based Systems and Software

Engineering (CBSE), which will take place on June 18-19, 1997, and the

Fifth Israeli Symposium on Theory of Computing and Systems (ISTCS'97),

which will take place on June 17-19, 1997.


Paper Submission: Submit three hard copies of an extended abstract (4-10

pages), or full paper, by February 2nd 1997, to

Leo Joskowicz

Institute of Computer Science

The Hebrew University of Jerusalem

Givat Ram, Jerusalem 91904, Israel

E-mail: josko(at)cs(dot)huji(dot)ac(dot)il


Authors will be notified of acceptance by 20th March 1997. A final version

of the accepted will appear in the conference preprints, which will be

distributed to participants at the symposium. Selected refereed full

length papers will be published in a special issue of the Annals of

Mathematics and Artificial Intelligence as a permanent record of the

Symposium. These should be submitted shortly after the conclusion of the

Symposium.


Information on registration, accommodations, etc., will appear in future

announcements, or contact: bisfai(at)cs(dot)biu(dot)ac(dot)il.

The web page site is:

<http://www.cs.biu.ac.il:8080/~schwart/bisfai97.html>


Symposium Chair
S. Kraus (Bar-Ilan U.)
Program Co-Chairs
D. Lehmann (Hebrew U.)
L. Joskowicz (Hebrew U.)



eof

1996

Issue 7

Date: 19 Nov 1996

TOPICS:

1. CFP AI-ED 97 Kobe, Japan. Deadline January 23rd 1997 (partial)

2. Call for Participation KBCS - Bombay, India. Dec 16-18 1996 (partial)

3. Subject: UM97 CFP - Deadline Nov 25 1996 (full)


Topic 1:

From: miz(at)ei(dot)sanken(dot)osaka-u(dot)ac(dot)jp (Riichiro MIZOGUCHI)

Subject: CFP AI-ED 97 Kobe, Japan. Deadline January 23rd 1997

NOTE: Full call for paper on the Web.


CALL FOR PAPERS

A I - E D 9 7

8TH WORLD CONFERENCE ON ARTIFICIAL INTELLIGENCE IN EDUCATION

--- Knowledge and Media in Learning Systems ---


19th - 22nd August, 1997

Kobe International Conference Center, JAPAN

URL: http://www.ei.sanken.osaka-u.ac.jp/aied97/cfp.html


Co-Sponsored by:

Artificial Intelligence in Education Society(AI-ED) and

Japanese Society for Information and Systems in Education(JSISE)


In Cooperation with:

Asia-Pacific Chapter of the AACE

Japanese Association for Artificial Intelligence


The 8th World Conference on Artificial Intelligence in Education

(AI-ED 97) is one of a series of international conferences designed to

report the best research in the field of AI in Education and to

provide opportunities for the cross-fertilisation of information and

ideas on research and applications in this field.


The theme for 1997 will be Knowledge and Media in Learning Systems,

and papers that explore the emerging roles of intelligent multimedia

and distributed technologies as well as computer supported

collaboration within that theme will be particularly welcome.


You are invited to submit proposals for research papers, survey papers,

themed papers, posters, tutorials, workshops, and panels.

All proposals will be reviewed for inclusion in the technical program.


Scope


The technical program focuses on research activities linking

Artificial Intelligence theories and techniques with Educational

theory and practice. Areas of interest include but are not limited to:


Agents

Architectures

Authoring systems and tutoring shells

Case-based systems

Cognitive development

Cognitive diagnosis

Collaboration and collaborative tools

Computer-assisted language learning

Conceptual change

Educational robotics

Evaluation of instructional systems

Human factors and interface design

Intelligent multimedia and hypermedia systems

Intelligent tutoring systems

Knowledge and skill acquisition

Knowledge representation for instruction

Learning environments and microworlds

Modelling pedagogical interactions

Motivation

Natural language interfaces

Networked learning and teaching systems

Non-standard and innovative interfaces

Principles and tools for instructional design

Social and cultural aspects of learning

Student modelling

Higher-order thinking skills and metacognition

Theories of teaching

Visual and graphical interfaces


+In addition to RESEARCH papers and posters in the above areas, SURVEY

papers will also be accepted. A survey paper will offer a coherent and

critical summary of achievements and outstanding problems in an area.


+To provoke debate and reflection, THEME papers are also sought under

the specific title "Knowledge and Media in Learning Systems - the next

15 years".


+Exhibits are expected to be an integral part of the AI-ED 97

conference. Companies or institutions offering to exhibit AI-ED

products are invited.


Topic 2:

From: KBCS Word Processing <kbcs(at)cs(dot)uni-sb(dot)de

IMPORTANT DATES

PAPERS AND POSTERS

Monday, Receipt by e-mail of abstracts and
25 November 1996 author information
Monday, Receipt of electronic submissions
2 December 1996 (optional)
Tuesday, E-mail notification to authors if the
3 December 1996 requirement of hard-copy submission is waived
Friday, Receipt of 5 hard copies of each
6 December 1996 manuscript (except where the hard-copy requirement was waived on 3 December)
Wednesday, Notification of authors by e-mail about
26 February 1997 acceptance or rejection of submissions
Monday, Receipt of electronic versions of
31 March 1997 camera-ready papers and summaries of posters


DOCTORAL CONSORTIUM

Wednesday, Receipt by e-mail of 3-page submissions
5 February 1997 as ASCII text
Wednesday, Notification to authors by e-mail about
5 March 1997 acceptance or rejection of submissions
Monday, Receipt of electronic versions of
31 March 1997 camera-ready summaries of presentations


WORKSHOPS


Monday, Receipt by e-mail of 3-page workshop
20 January 1997 proposals as ASCII text
Friday, Notification by e-mail to workshop
14 February 1997 proposers about acceptance or rejection of proposals
Friday, Submission, by proposers of accepted
21 February 1997 workshops, of final calls for participation
Tuesday, Availability via the UM97 Web site
25 February 1997 and by e-mail of calls for participation in workshops


SYSTEM DEMONSTRATIONS


Tuesday, Registration of system demonstrations
15 April 1997 by e-mail


REASONS TO SUBMIT TO UM97


As a potential author, you may now be wondering whether to

write up your work for UM97 or for a journal or another conference.

Here are some points to bear in mind:


1. A paper that appears in the proceedings will have the status of a

peer-reviewed publication in an internationally distributed

edited volume, which will be published by SpringerWien-New York.

2. As an additional means of ensuring accessibility of the

proceedings, electronic versions of the papers will remain

available on the World Wide Web site of User Modeling, Inc.

for a long time after the conference.

3. Publication in the proceedings volume can be viewed as a

step along the way to the production of a major journal article

about your research. The deadline will encourage you to produce

an initial version; the comments of the members of the international

program committee will help you to improve it; and the feedback

that you get on the final conference paper will help you to

produce a strong full journal manuscript. Journal editors will

not in general be bothered by the fact that a related

conference-length paper has been published, as long as your

journal submission is sufficiently longer, more detailed, and

otherwise expanded relative to the conference paper. (The journal

"User Modeling and User-Adapted Interaction" is already reserving

space for articles of this sort.)

4. Experience with previous conferences in the UM series has

shown that they provide an exceptionally good environment for

exchanging ideas and making new contacts. There is a sharp

contrast with broader conferences, at which it is often hard to

find someone who is interested in the same topics as you are.

5. Finally, people who have visited Sardinia often claim that

it is one of the most beautiful places the world. There is

nothing wrong with enjoying this beauty for a few days before or

after UM97.


eof

Issue 6

Date: 20 Oct 1996




TOPICS:

1. E W N L G - 9 7 6th European Workshop on Natural Language Generation

DEADLINE NOV 15 1996!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

2. Post in Computational Linguistics, Stirling <jld1(at)stir(dot)ac(dot)uk>

3. Practical Human-computer conversation 1997 <yorick(at)dcs(dot)shef(dot)ac(dot)uk>







Topic 1:

From: he232ho(at)rs1-hrz(dot)uni-duisburg(dot)de (Wolfgang Hoeppner)

Subject: EWNLG-97

CALL FOR PAPERS


E W N L G - 9 7


6th European Workshop on

Natural Language Generation


March 24 - 26, 1997


Gerhard-Mercator University, Duisburg, Germany


The workshop aims to bring together researchers interested in Natural

Language Generation from such different perspectives as Linguistics,

Artificial Intelligence, Psychology, Cognitive Science, and Engineering.

The meeting continues the tradition of a series of workshops held

biannually in Europe (Royaumont, 1987; Edinburgh, 1989; Judenstein,

1991; Pisa, 1993; and Leiden, 1995) but it is open to researchers from

all over the world.


Program Committee:

Stephan Busemann, Saarbruecken

Alison Cawsey, Edinburgh

Robert Dale, Sydney

Wolfgang Hoeppner, Duisburg (chair)

Richard Kittredge, Montreal

Stephan Mehl, Duisburg

Koenrad deSmedt, Bergen

Michael Zock, Paris


Papers, posters and demonstrations are invited on original and

substantial work related to the automatic generation of natural

language, including computational linguistics research, artificial

intelligence methods, computer models of human language processing,

empirical research, and the development and evaluation of applied

systems. Contributions on all aspects of natural language generation are

welcome, but the special theme of this workshop will be

'System Architectures for Text Generation'.


This topic comprises a variety of more specific questions, e.g. planning

and/or schemata, pragmatic impact on content selection and form

determination, serial or incremental processing, macro-planning and

micro-planning.


To encourage a workshop atmosphere while allowing a relatively large

number of people to participate, selected papers will be given large time

slots including ample discussion time; other papers will be grouped for

shorter presentations and mutual interaction, and there will be sessions

for posters and computer demonstrations.


Submissions:


Researchers wishing to present a PAPER are requested to submit three

copies of an original unpublished article (10 pages). To allow for

anonymous reviewing the name(s) and complete adress(es) of the

author(s) have to be provided on a separate sheet. We would appreciate

that you additionally send an electronic version of the paper (email or

diskette).


Researchers wishing to present a POSTER are invited to submit three

copies of a reduced version of their poster on 4 normal pages that

together form an A2 size sheet. Use a normal character size. As with

papers any personal information about the author(s) should appear on a

separate sheet.


Researchers wishing to demonstrate a computer PROGRAM are invited to

send three copies of a short description of their program together with

some examples of input and output and hardware requirements. Please

include the name(s) and complete address(es) of the author(s) in the

description.

********** N E W D E A D L I N E *************

All contributions must be sent BEFORE NOVEMBER 15, 1996 to the

Program Chairman at the following address:


Prof. Dr. Wolfgang Hoeppner

Gerhard-Mercator University, Duisburg

FB3 * Computational Linguistics

D-47048 Duisburg, Germany


Tel.: +49 203 379-2006/2008

email: hoeppner(at)unidui(dot)uni-duisburg(dot)de


Internet: http://verdi.uni-duisburg.de/EWNLG-96.html


Authors will be notified about acceptance or rejection by January 17, 1997.


Local arrangements:


Local arrangements are handled by: Wolfgang Hoeppner and Stephan

Mehl (University of Duisburg).


The meeting will be held from the morning of Monday March 24, 1997

through afternoon on Wednesday 26, in 'Die Wolfsburg' situated in the

municipal forest of Duisburg. This conference site congresses and

workshops from all scientific areas and is equipped with excellent

presentation facilities and modern guest rooms.


The cost of the workshop to each participant is currently estimated at

about DM 500 including accommodation and meals, but the participants'

fee may turn out to be lower depending on funding. The workshop will

also be open to a limited number of participants not contributing a

paper, poster or demo. A call for participation including more

information and a registration form will be sent out later as soon as the

program has been put together.


Please direct any inquiries to the adress above.

---------->------->----->--->->>> <<<-<---<-----<-------<----------


Prof. Dr. Wolfgang Hoeppner *********

Gerhard-Mercator-Universitaet Duisburg *======*

Fachbereich 3 * Computerlinguistik *====*

D-47048 Duisburg *==*

*

Tel.: (0203) 379-2006/2008

email: hoeppner(at)unidui(dot)uni-duisburg(dot)de

internet: http://verdi.uni-duisburg.de/hoeppner.html

or: http://verdi.uni-duisburg.de/Englisch/hoeppner.html

---------->------->----->--->->>> <<<-<---<-----<-------<----------




Topic 2:

From: Dr Judy L Delin <jld1(at)stir(dot)ac(dot)uk>

Subject: Post in Computational Linguistics, Stirling


Lectureship in Computational and Descriptive Linguistics

University of Stirling, Scotland


The University wishes to expand its growing activity in descriptive and

computational linguistics by appointing a Lecturer to work alongside Dr.

Judy Delin in the Department of English Studies.


We are looking for an established researcher in the field who will invest in

the development of research and teaching at Stirling, with expertise in

discourse, pragmatics, contrastive text analysis, natural language

generation, and/or speech generation. Experience or an interest in

contrastive text analysis in languages other than English, especially

Japanese, would be particularly desirable. The level of the appointment

reflects our expectation that the new person will be able to generate

external research funds and will have initiative in developing

collaborative research within and outside the group. The post will be

research-led, but the ideal candidate would also be able to help develop

future undergraduate and postgraduate teaching modules in linguistics

and computational linguistics. Future teaching and our research

development will also require expertise in programming for NLP.


Stirling is a small University situated in what is perhaps the most

beautiful campus in the U.K., and within easy reach of Edinburgh and

Glasgow. The accommodation is modern and well-equipped (networked,

Unix workstation or other platform if preferred). The Lecturer will be part

of the Language and Communication Research Group, an interdisciplinary

group that includes researchers from Psychology, Education, English

Studies, Japanese Studies, and the Centre for English Language

Teaching. Initiative in establishing further cross-disciplinary links will be

particularly encouraged.


The post would be for two years in the first instance with good prospects of

renewal. The appointment will be on the Lecturer B Scale, L. 20677 to

L. 26430 a year, with placement according to qualifications, experience,

and potential. Starting date is negotiable, although we hope that the new

Lecturer will be with us by January 1997.


Informal enquiries are welcome: please contact Dr Judy Delin on(+44) (0)

1786 467974, email: jld1(at)stir(dot)ac(dot)uk, or consult the Web page at

http://www.stir.ac.uk/english/Communication/post.html. Anyone sending

email or making an enquiry will be informed of the official closing date,

which is likely to be during September 1996, and will be sent a copy of

the further particulars for the post once this date is finalised with

our Staff Office.


Dr Judy Delin

Department of English Studies/Language and Communication Research Group

University of Stirling

Stirling FK9 4LA

Scotland


Tel: (+44) (0) 1786 467974

Fax: (+44) (0) 1786 466201

email: jld1(at)stir(dot)ac(dot)uk

URL: http://www.stir.ac.uk/english/Communication/post.html





Topic 3:

From: Yorick Wilks <yorick(at)dcs(dot)shef(dot)ac(dot)uk>

Subject: Practical Human-computer conversation by Lake Como 1997


CALL FOR EXPRESSIONS OF INTEREST: PLEASE RECIRCULATE THIS WIDELY


1st INTERNATIONAL WORKSHOP ON HUMAN-COMPUTER CONVERSATION


Bellagio, Italy, 14-16 July, 1997

We are seeking expressions of interest before formally

announcing a rather different kind of workshop: one that

will survey and demonstrate techniques for practical,

plausible, human computer conversation. The workshop would

be in the spirit of the Loebner Competition meetings, but

would not constitute any kind of "Turing" competition

under controlled deception conditions, but would, we hope,

give opportunity for extensive demonstrations of

working conversational systems, preferably without domain

restrictions.


As well as practical demonstrations we would hope for papers

and discussions on How-To-Do-It: including abstract

discussions of the computer individual as well as reports of

practical experiences of using the large resources and knowledge data

bases now available through forms of information retrieval

and natural language processing and their impact (together

with fast access techniques) on high-quality conversation

simulations. The meeting is not intended to be yet another

get together on linguistic methods for dialogue modelling

or human-computer interaction, but rather based on the

assumption that, in a range of places, great strides are

actually being made in real conversation simulations from

practical techniques and points of view, and that all would

benefit from face-to-face interaction on this, as well as

exploring the industrial/commercial applications of these

technologies in HCI/WWW environments in the very near

future.


The proposed site is the Grand Hotel Villa Serbelloni,

in Bellagio, Italy, on Lake Como, the

legendary site of Pliny's villa where the two arms of the

lake meet, and one of the most beautiful spots in the world,

though easily reached from Milan. The date, 14-16 July 1997,

immediately follows the EACL/ACL in Madrid.

Working system demonstrations

would be central, and there would also be a range of panels

on aspects of the state of the art.


Interest is solicited by email at the address below from anyone

with new ideas, results or ongoing work to report on any aspect of

human-computer conversation, or those with an interest in or commitment

to the exploitation of this technology.

The emphasis should be on the software techniques for

communication in natural language and NOT on speech recognition

or speech synthesis. Given sufficient interest

a committee will be established and conditions for submission

announced before the end of November 1996. Please put

Serbelloni in the message line of your email. Updatings of

developments for this workshop will be posted to:

http://www.dcs.shef.ac.uk/research/ilash/Meetings/Bellagio/

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

Professor Yorick Wilks

AI and NN Research Group,

Department of Computer Science

University of Sheffield

Regent Court

211 Portobello St.,

Sheffield S1 4DP

UK


phone: (44) 114 282 5561

fax: (44) 114 278 0972

email: yorick(at)dcs(dot)shef(dot)ac(dot)uk

www: http://www.dcs.shef.ac.uk/People/Y.Wilks

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





eof




Issue 5

Date: 07 Jul 1996

————————

======================================================================

TOPICS:

1. User Modeling Conference 1st CFP - <Cecile.Paris@itri(dot)brighton(dot)ac(dot)uk>

2. Generation thesis available - Lexical Semantics and Knowledge

Representation in Multilingual Sentence Generation - <stede@cs(dot)tu-berlin(dot)de>

3. Call for Participants - TALC96 - TEACHING AND LANGUAGE CORPORA

Lancaster University, UK, 9th-12th August, 1996 - <spb@comp(dot)lancs(dot)ac(dot)uk>

4. 2nd CFP - International Conference on Knowledge Based Computer Systems

Bombay, India - December 16-18, 1996 - Deadline Aug 15, 1996 - <kbcs@konark(dot)ncst(dot)ernet(dot)in>

======================================================================

Topic 1:

Subject: UM97: FIRST CALL FOR PAPERS

Date: June 2-5 1997 - Deadline 25 November 1996

From: Cecile Paris <Cecile.Paris@itri(dot)brighton(dot)ac(dot)uk>


UM97


SIXTH INTERNATIONAL CONFERENCE ON USER MODELING
Chia Laguna, Sardinia, Italy, June 2-5 1997


http://www.cs.uni-sb.de/UM97/ or
http://www.crs4.it/UM97/


Contents:

Background

Conference Topics

Conference Organization

Brief Submission Instructions

Contact Addresses

Important Dates


————————————— BACKGROUND ——————————————

User modeling has been found to enhance the effectiveness

and/or usability of software systems in a wide variety of

situations. A user model is an explicit representation of

properties of a particular user. A system that constructs and

consults user models can adapt diverse aspects of its performance

to individual users.


Techniques for user modeling have been developed and evaluated

by researchers in a number of fields, including artificial

intelligence, education, psychology, linguistics, human-computer

interaction, and information science.


The International Conferences on User Modeling provide a forum

in which academic and industrial researchers from all of these

fields can exchange their complementary insights on user modeling

issues. The size and format of the meetings support intensive

discussion, which often continues long after the conference has

ended.


UM97 follows the Fourth and Fifth International Conferences on

User Modeling, which took place in Cape Cod, Massachusetts, in

August 1994 and Kailua-Kona, Hawaii in January 1996,

respectively. UM97 will include tutorials, invited talks, paper

and poster sessions, a doctoral consortium, workshops, and system

demonstrations.


Accepted papers, as well as summaries of other conference

contributions, will be published in a proceedings volume.

Information about the form of this publication will be made

available via the conference World Wide Web site. The Web site

will also provide access to electronic versions of contributions

to the conference.


The journal "User Modeling and User-Adapted Interaction" is

reserving space for expanded versions of the best papers of UM97.

A $500 Best Paper Award is being sponsored by Kluwer Academic

Publishers.


UM97 is being sponsored by AI*IA, the Italian Association for

Artificial Intelligence.

——————————— CONFERENCE TOPICS ————————————

The following nonexhaustive list gives some examples of topics

that are relevant to UM97:


Construction of models of users' ...


* knowledge, beliefs, and misconceptions,

* preferences,

* goals and plans,

* typical behaviors,

* cognitive styles, ....


Exploitation of user models to achieve ...


* adaptive information filtering and retrieval,

* tailored information presentation,

* transfer of task performance from user to system,

* selection of instructional interventions,

* interface adaptation, ....


Inference techniques involving ...


* neural networks,

* psychometric methods,

* numerical uncertainty management,

* epistemic logic or other logic-based formalisms,

* default reasoning and truth maintenance,

* stereotype hierarchies, ....


Practical issues of ...


* privacy and user model inspectability,

* user model consistency,

* empirical evaluation,

* standardization of user modeling shell systems, ....


Systems for adaptive ...


* tutoring and provision of learning environments,

* explanation of system actions,

* on-line aiding,

* hypermedia and multimodal interaction,

* knowledge-based presentation design,

* product presentation,

* information management on the Internet,

* support of end-user programming,

* accommodation of users with special needs,

* support of collaboration, ....

—————————— CONFERENCE ORGANIZATION ——————————

General Chair:
Carlo Tasso University of Udine, Italy
Organizing Chair:
Alessandro Micarelli University of Rome 3, Italy
Program Co-Chairs:
Anthony Jameson University of Saarbruecken, Germany
Cecile Paris University of Brighton, UK
Program Committee:
Nicholas J. Belkin Rutgers University, USA
Beatrice Cahour CNRS Rouen, France
Sandra Carberry University of Delaware, USA
Albert Corbett Carnegie Mellon University, USA
Fiorella de Rosis University of Bari, Italy
Oren Etzioni University of Washington, USA
Gerhard Fischer University of Colorado, Boulder, USA
Helen M. Gigley Office of Naval Research, USA
Brad Goodman The MITRE Corporation, USA
Eric Horvitz Microsoft Research, USA
Judy Kay Sydney University, Australia
Alfred Kobsa GMD FIT, Germany
Diane Litman AT&T Research, USA
Pattie Maes MIT Media Lab, USA
Uwe Malinowski Siemens Corporate R&D, Germany
Gordon McCalla University of Saskatchewan, Canada
Michael McTear University of Ulster, UK
Alessandro Micarelli University of Rome 3, Italy
Robert J. Mislevy Educational Testing Service, USA
Riichiro Mizoguchi Osaka University, Japan
Edie M. Rasmussen University of Pittsburgh, USA
John Self University of Leeds, UK
Julita Vassileva Federal Armed Forces Univ., Germany
Wolfgang Wahlster DFKI, Germany
Geoff Webb Deakin University, Australia
Ingrid Zukerman Monash University, Australia
Doctoral Consortium Organizers:
Nadja De Carolis University of Bari, Italy
Fiorella de Rosis University of Bari, Italy
Workshop Coordinator:
Christoph G. Thomas GMD FIT, Germany
Demonstration Organizer:
Giorgio Brajnik University of Udine, Italy


UM97 is being organized jointly by the Department of

Mathematics and Computer Science of the University of Udine, the

Department of Scientific Disciplines of the University of Rome 3,

the Department of Informatics of the University of Bari, and CRS4

(Center for Advanced Studies, Research and Development in

Sardinia), under the auspices of User Modeling, Inc.


———————— BRIEF SUBMISSION INSTRUCTIONS —————————

PAPERS AND POSTERS


Submissions are invited that describe original academic or

industrial research on some aspect of user modeling.


Papers should describe significant, mature research; they will

be published in full length in the proceedings and presented in

talks at the conference.


Posters typically describe research which does not yet

represent a substantial advance but which can stimulate the

exchange of ideas. Summaries of posters will be included in the

proceedings.


The timetable and the length requirements for poster and paper

submissions are the same. Submissions to the poster category may

make more use of graphics and tables than is usual for paper

submissions, but they must be self-explanatory. If the authors do

not indicate a preference for the paper or poster category, the

program committee will judge which category is more appropriate.


Submissions must fit within 12 single-spaced pages printed with

a 12-point font. These 12 pages must include all elements of the

submission. Page 1 must include the title of the paper, a short

abstract (150 words), a list of keywords, and the authors' postal

and e-mail addresses and fax and phone numbers. The abstract and

the author information on Page 1 must also be included in an

e-mail message that is sent to the program co-chairs one week

before the submission of the manuscript.


A manuscript can be submitted either electronically (as a

PostScript file) or as hard copy. Details of the procedure for

electronic submission will be found in the full submission

instructions for UM97, which authors can obtain via the

conference Web site or by e-mail from the program co-chairs.


All authors should obtain these full submission instructions,

which will also contain information about style files designed to

facilitate manuscript preparation and general tips on how to

maximize the likelihood of acceptance.


DOCTORAL CONSORTIUM


The doctoral consortium will offer PhD students a chance to

discuss their plans and the intermediate results of their

research with a diverse and knowledgeable international audience.


Summaries of the accepted presentations will be included in the

proceedings volume.


Further information on the doctoral symposium, including

information about possible sources of funding, can be obtained

via the UM97 Web site and by e-mail from the doctoral consortium

organizers.


WORKSHOPS


Half-day workshops will permit discussion and debate on topics

of current interest. The format for each workshop will be


determined by the proposer of that workshop, who will also set

any necessary deadlines for participants. Before submitting a

proposal, each proposer should obtain instructions and advice via

the conference Web site and/or by e-mail from the UM97 workshop

coordinator.


SYSTEM DEMONSTRATIONS


Various platforms will be available for unrefereed system

demonstrations. Prospective presenters should contact the

demonstration organizer by e-mail and specify their hardware and

software requirements.

——————————— CONTACT ADDRESSES ————————————

Up-to-date conference information and detailed submission

instructions can be obtained via either of the following World

Wide Web sites:


http://www.cs.uni-sb.de/UM97/ (site in Germany) or

http://www.crs4.it/UM97/ (site in Sardinia)


The following addresses can be used for queries and (where

applicable) for submissions:


ORGANIZING CHAIR


um97-organization@cs.uni-sb.de

Fax: Alessandro Micarelli, +39-6-5573030


PROGRAM CO-CHAIRS:


um97-papers@cs.uni-sb.de

Hard-copy submissions:

Anthony Jameson

Department of Computer Science

University of Saarbruecken

Stuhlsatzenhausweg, Building 36.1

66125 Saarbruecken, Germany

Phone: +49-681-302-2474


DOCTORAL CONSORTIUM ORGANIZERS

um97-doctoral@cs.uni-sb.de


WORKSHOP COORDINATOR

um97-workshops@cs.uni-sb.de


DEMONSTRATION ORGANIZER

um97-demos@cs.uni-sb.de

———————————— IMPORTANT DATES ————————————


PAPERS AND POSTERS
Monday, Receipt by e-mail of abstracts and
25 November 1996 author information
Monday, Receipt of electronic submissions
2 December 1996 (optional)
Tuesday, E-mail notification to authors if the
3 December 1996 requirement of hard-copy submission is waived
Friday, Receipt of 5 hard copies of each
6 December 1996

manuscript (except where the hard-copy requirement was waived on 3 December)

Wednesday, Notification of authors by e-mail about
26 February 1997 acceptance or rejection of submissions
Monday, Receipt of electronic versions of
31 March 1997 camera-ready papers and summaries of posters
DOCTORAL CONSORTIUM
Wednesday, Receipt by e-mail of 3-page submissions
5 February 1997 as ASCII text
Wednesday, Notification to authors by e-mail about
5 March 1997 acceptance or rejection of submissions
Monday, Receipt of electronic versions of
31 March 1997 camera-ready summaries of presentations
WORKSHOPS
Monday, Receipt by e-mail of 3-page workshop
20 January 1997 proposals as ASCII text
Friday, Notification by e-mail to workshop
14 February 1997 proposers about acceptance or rejection of proposals
Friday, Submission, by proposers of accepted
21 February 1997 workshops, of final calls for participation
Tuesday, Availability via the UM97 Web site
25 February 1997 and by e-mail of calls for participation in workshops
SYSTEM DEMONSTRATIONS
Tuesday, Registration of system demonstrations
15 April 1997 by e-mail


======================================================================

Topic 2:

Subject: Generation thesis available

Date: 20 June 1996

From: Manfred Stede <stede@cs.tu-berlin.de>


Manfred Stede: Lexical semantics and knowledge representation in

multilingual sentence generation.

University of Toronto, Dept. of Computer Science, 1996.


This thesis develops a new approach to automatic language generation

that focuses on the need to produce a range of different {\em

paraphrases} from the same input representation. One feature of the

system is its solidly grounding representations of word meaning in a

background knowledge base, which enables the production of paraphrases

stemming from certain inferences, rather than from purely lexical

relationships alone.


The system is designed in such a way that the paraphrasing mechanism

extends naturally to a {\em multilingual} generator; specifically, we

will be concerned with producing English and German sentences. The

focus of the system is on {\em lexical} paraphrases, and one of the

contributions of the thesis is in identifying, analyzing and extending

relevant linguistic research so that it can be used to handle the

problems of lexical semantics in a language generation system. The

{\em lexical entries} are more complex than in previous generators,

and they separate the various aspects of word meaning, so that

different ways of paraphrasing can be systematically related to the

different motivations for saying a sentence in a particular way. One

result of accounting for lexical semantics in this fashion is a

formalization of a number of {\em verb alternations}, for which a

generative treatment is given.


While the actual {\em choice} of one paraphrase as the best-suited utterance

in a given situation is not a focal point of the thesis, two dimensions

of {\em preferring} a variant of a sentence are discussed: that of

assigning {\em salience} to the different elements of the sentence, and

that of {\em connotational} or {\em stylistic} features of the utterance.

These dimensions are integrated into the system, and it can thus

determine a preferred paraphrase from a set of alternatives.


To demonstrate the feasibility of the approach, the proposed

generation architecture has been implemented as a protoype, along with a

domain model that serves as the background knowledge base for specifying

the input to the generator. A range of generated examples is presented

to show the functionality of the system.


> If interested in either a hardcopy or a postscript file, please

> contact the author at stede@cs.tu-berlin.de


======================================================================

Topic 3:

Subject: Call for Participants TALC96 - Teaching and Language Corpora

Date: Lanncaster University, UK, 9th-12th August, 1996

From: "Mr S P Botley" <spb@comp.lancs.ac.uk>


CALL FOR PARTICIPANTS
TALC96 - TEACHING AND LANGUAGE CORPORA
Lancaster University, UK, 9th-12th August, 1996
<http://www.comp.lancs.ac.uk/computing/research/ucrel/talc/>


AIMS OF THE CONFERENCE

While the use of computer text corpora in research is now well

established, they are now being used increasingly for teaching

purposes. This includes the use of corpus data to inform and create

teaching materials; it also includes the direct exploration of corpora

by students, both in the study of linguistics and of foreign languages.


Talc96 will build upon the success of Talc94, which brought together

researchers and teachers who are involved in such work, to take part in

an international exchange of current experience and expertise.


THEMES

KEY THEME: Talc96 will have a special focus on evaluating the claims

made for corpora in linguistics and language teaching.


OTHER THEMES: which the conference is expected to cover include -


1.) The use of corpora in student led learning and investigation.

2.) Software for corpus based language and linguistics learning.

3.) Developing corpora for teaching purposes.

4.) The exploitation of corpus based teaching and learning materials.

5.) The theory and practice of corpus based teaching and learning.


WORKSHOPS

Talc96 will also host several workshops related to teaching and

language corpora. To give an example of what those workshops may be,

Talc94 had a variety of workshops such as "Multilingual Corpus

Building" and "Concordancing and Corpus Retrieval". Workshops will be

of one to two hour duration.


TALC96 - Programme of Events


Is available at <http://www.comp.lancs.ac.uk/computing/research/ucrel/talc/>


Please register BEFORE 21st July 1996, otherwise we cannot guarantee

availability of accommodation.


======================================================================

Topic 4:

Subject: KBCS-96 (2nd CFP) Deadline Extended

Date: Wed, 26 Jun 1996 - Deadline 15 August 1996

From: KBCS Word Processing <kbcs@konark.ncst.ernet.in>

Second Call for Papers
INTERNATIONAL CONFERENCE ON
KNOWLEDGE BASED COMPUTER SYSTEMS
National Centre for Software Technology
Bombay, India
December 16-18, 1996


THE DEADLINE FOR SUBMISSION OF PAPERS HAS NOW BEEN EXTENDED TO AUGUST 15, 1996

URL : http://konark.ncst.ernet.in/~kbcs/kbcs96.html

____________________________________________________________________________ The International Conference on Knowledge Based Computer Systems will be held

in Bombay, India during December 16-18, 1996. The conference is intended to

act as a forum for promoting interaction among researchers in the field of

Artificial Intelligence in India and abroad. There will be a two day

conference during December 16-17, 1996 followed by one day of

post-conference tutorials on December 18, 1996.


Papers are invited on substantial, original and unpublished research on

all aspects of Artificial Intelligence, including, but not limited to the

following:

o AI Applications o AI Architectures
o Artificial Life o Automatic Programming
o Cognitive Modeling o Expert Systems
o Foundations of AI o Genetic Algorithms
o Information Retrieval o Intelligent Tutoring Systems
o Knowledge Acquisition o Knowledge Representation
o Machine Learning o Machine Translation
o Natural Language Processing o Neural Networks
o Planning and Scheduling o Reasoning
o Robotics o Search Techniques
o Speech Processing o Theorem Proving
o Uncertainty Handling o User Interfaces
o User Modeling o Vision


Programme Committee:


S. Arunkumar, IIT, Bombay Amitava Bagchi, IIM, Calcutta
Pushpak Bhattacharya, IIT, Bombay Margaret A. Boden, U of Sussex, UK
Nick Cercone, U of Regina, Canada B. B. Chaudhuri, ISI, Calcutta
R. Chandrasekar, NCST, Bombay S. K. Goyal, GTE Labs , USA
S. S. Gupta, TUL, Bombay J. R. Isaac, NIIT, New Delhi
Aravind K. Joshi, R. A. Kowalski, Imperial College, UK
U of Pennsylvania, USA
H. N. Mahabala, INFOSYS, Bangalore M. Narasimha Murthy, IISc, Bangalore
R. Narasimhan, CMC, Bangalore S. Ramani, NCST, Bombay (Chair)
P. V. S. Rao, TIFR, Bombay Patrick Saint-Dizier,U of Paul Sabatier, France
R. Sangal, IIT, Kanpur R. Uthurusamy, GMR, USA
M. Vidyasagar, CAIR, Bangalore

Format of Submission:


Authors should submit their papers, not to exceed 5000 words (including

figures and references) either electronically or in hard copy. Papers

should be in English. Papers should include an abstract of about 100-200

words in length. Papers outside the specified length are subject to

rejection without review. Since reviewing will be "blind", the authors'

names and affiliations along with the main area of the paper should be given

only on a separate cover sheet. Hard copy submissions should be sent in

triplicate. Papers in electronic form can be in any of the following

formats: plain text, Postscript, Latex, Microsoft Word, or Wordstar.

Submissions in electronic form are preferred.


Send papers to the KBCS-96 Secretariat at the address below.


Paper Submission Deadlines:

o Papers due: August 15, 1996

o Acceptance Notification: October 15, 1996

o Camera Ready Copy due: December 1, 1996


Call for Tutorials:


Proposals are invited for post-conference tutorials. Tutorials can be

half-day or full-day, and will be held on December 18th, 1996. The

proposal should be presented in the form of a 200-word abstract, one page

topical outline of the content, description of the proposers and their

qualifications relating to the tutorial content.


Tutorial Submission Deadlines:


o Proposal Submission: July 31, 1996

o Acceptance Notification: August 31, 1996

o Complete Tutorial materials due: December 1, 1996


Send proposals to the KBCS-96 Secretariat at the address below.


Organizing Committee:

George Arakal, NCST (Chair) K.S.R. Anjaneyulu, NCST
P. Ravi Prakash, NCST Durgesh D. Rao, NCST
M. Sasikumar, NCST T. Suresh, NCST


For further information please refer to the KBCS-96 home page or

write to the KBCS-96 Secretariat.

___________________________________________________________________________

Address

KBCS-96 Secretariat Phone : +91 (22) 620 1606
National Centre for Software Technology Fax : +91 (22) 621 0139
Gulmohar Cross Rd No. 9 E-mail : kbcs@konark.ncst.ernet.in
Juhu, Bombay 400 049, India

URL : http://konark.ncst.ernet.in/~kbcs/kbcs96.html

——————————————————————————————————————

======================================================================

eof

======================================================================

Retrieved from "https://aclweb.org/aclwiki/index.php?title=SIGGEN:_Newsletter_Archive&oldid=11303"