LINGUIST List 12.1098

Fri Apr 20 2001

Calls: Textual Data, Natural Language Generation

Editor for this issue: Jody Huellmantel <>

As a matter of policy, LINGUIST discourages the use of abbreviations or acronyms in conference announcements unless they are explained in the text.


  1. Pascale S�billot, Statistical Analysis of Textual Data (JADT 2002)
  2. Nicolas Nicolov, Natural Language Generation (ACL NLG)

Message 1: Statistical Analysis of Textual Data (JADT 2002)

Date: Fri, 20 Apr 2001 19:59:35 +0200
From: Pascale S�billot <>
Subject: Statistical Analysis of Textual Data (JADT 2002)

CALL FOR PAPERS - JADT 2002 - March 13-15, 2002

6th International Conference on the Statistical Analysis of Textual Data

March 13-15, 2002 
Palais du Grand Large 
St-Malo / France

The International Conference on the Statistical Analysis of Textual Data
provides a workshop-style forum to all scholars, statisticians, computer
scientists, linguists..., working in the vast field of textual data
analysis ranging from lexicography to the analysis of political
discourse, from documentary research to marketing research, from
computational linguistics to sociolinguistics, from the processing of
data to content analysis. Following Barcelona (1990), Montpellier
(1993), Rome (1995), Nice (1998) and Lausanne (2000), the 6th
International Conference will be held in Saint-Malo, France on march
13-15 2002. 

Important Dates
 Submission Deadline: September 1, 2001
 Notification: October 30, 2001
 Camera ready papers: December 15, 2001
 Conference: March 13-15, 2002

e-mail address:


Submissions should be limited to original work. All papers should
include background survey and/or reference to previous works.
Participants wishing to submit a paper should send to the organization
committee (via email a first version of their paper
for review by September 1, 2001, giving the following information: 
 - Name, affiliation and full postal address (fax and/or e-mail) of authors 
 - Title of the proposed paper with keywords
 - A first version of the paper (12 pages max.) emphasizing the purpose
of the paper
 - An abstract in the paper language
 - An abstract in English (maximum 300 words) 
 - Bibliographical references 


Topics of interest of the conference concern the application of
statistical models and tools in the following domains:
 - Exploratory Textual Data Analysis 
 - Textual Statistics
 - Statistical Analysis of Responses to Open Questions
 - Natural Language Processing
 - Stylometry 
 - Documentary and Bibliometric Statistical Analysis 
 - Textual Classification
 - Text Corpora and Text Encoding 
 - Frequency Dictionaries 
 - Lemmatization, automatic categorization
 - Information Retrieval 
 - Software for Lexical and Textual Analysis 

Notification of acceptance will be sent to the authors on October 30,

Final versions (camera-ready papers) should conform to the format that
will be provided to the authors (12 pages max.) and reach the committee
no later than December 15, 2001. 

Accepted papers will be collected and issued as proceedings to the
participants at the start of the conference.

Submissions, communications and presentations can be made in any one of
these languages: English, French, Spanish, Italian
All communications and presentations must contain an English abstract.
As in the previous meetings, no translation will be provided. 

Program Committee:

Ramon Alvarez, Univ. of Leon, Spain
Harald Baayen, Univ. of Nim�gue, The Netherlands
Monica B�cue, Polyt. Univ. of Catalunya, Spain
Sergio Bolasco, Univ. of Roma 'La Sapienza', Italy
�tienne Brunet, Univ. of Nice Sophia Antipolis, France
Annibale Elia, Univ. of Salerno, Italy
Michel Kerbaol, INSERM, Univ. of Rennes 1, France
Dominique Labb�, Univ. of Grenoble, France 
Ludovic Lebart, CNRS, ENST Paris, France (Pr�sident)
Alain Lelu Univ. of Franche Comt�, France
Annie Morin, IRISA, Univ. of Rennes 1, France
Sylvie Mellet, CNRS, Nice, France
Martin Rajman, EPFL Lausanne, Switzerland
Max Reinert, CNRS, Univ. of Versailles SQY, France
Andr� Salem, Univ. Paris 3, France
Pascale S�billot, IRISA, France
Fiona Tweedie, Univ. of Glasgow, UK

Organization Committee:

Annie Morin, IRISA, Univ. of Rennes 1, Fr
Michel Kerbaol, INSERM, Univ. of Rennes 1, Fr 
Pascale Sebillot, IRISA, Univ. of Rennes 1, Fr
organized by IRISA/INRIA Rennes
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue

Message 2: Natural Language Generation (ACL NLG)

Date: Wed, 18 Apr 2001 04:17:27 -0400
From: Nicolas Nicolov <>
Subject: Natural Language Generation (ACL NLG)

 ACL/EACL 2001 Workshop


 6-7 July 2001
 Toulouse, France

 Sponsored by IBM, Endorsed by SIGGEN

- ----------------------------------------------------------------------
Natural language generation (NLG) constitutes the production of meaningful
texts in natural languages from some underlying non-linguistic
representation of information. Accomplishing this goal may be envisioned
for a number of different purposes, including standardized and/or
multi-lingual reports, summaries, machine translation, dialog 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, the production of referring
expressions, aggregation, lexicalization, and surface realization, as well
as coordination with other media.

This workshop is part of a bi-annual series of workshops about natural
language generation that runs since 1987. Previous European workshops have
been held at Royaumont, Edinburgh, Judenstein, Pisa, Leiden, Duisburg, and
Toulouse. The goal of the workshop is to be an informal meeting which
facilitates the dissemination of knowledge and expertise in the field. The
workshop will focus on the following topics:

 * Search methods for NLG (in content planning and realization)

 There seems to be a substantial discrepancy between
 application-oriented systems and principled approaches to NLG.
 Accomodating a standard pipeline architecture with suitable heuristic
 preferences to the intended functionality of a system stands in
 contrast to several principled approaches to searching which have been
 tried out so far. These include blackboard architectures, constraint
 propagation and, more recently genetic algorithms and statistical
 techniques. A comparison of these methods in terms of their potential
 and limitations is likely to improve understanding about this issue.
 Gained insights could prove fruitful for building applications in a
 more general and, thus, better reusable way, especially in large-scale
 applications such as summarization and machine translation.

 * Differences in information organization between source and
 presentation specifications (and methods to bridge between these)

 Whether the generation task is to verbally express contents of some
 knowledge base or to produce multi-lingual presentations from
 language-neutral or similar representations, there are strong
 similarities in building the target representations: In the
 overwhelming number of cases, the ordering and embedding of elements
 in the source representation is reflected by the ordering and
 embedding of their corresponding realizations at the surface. Often,
 this reflection is systematic, many times even simple. But a few cases
 prove complex and involve a major restructuring of the surface
 structure when compared to the source structure. A major emphasis of
 this topic is on collecting such complex cases, identifying
 commonalities between them and discussing restructuring techniques.

Accepted papers on these and related topics will be scheduled for
presentation. The majority of the time will be devoted to
discussions, either in sequence or in parallel, depending on the
number of participants. We are considering organizing a panel. For the
focus topics above, we will contact a number of competent researchers
to address the topic from a specific perspective according to their
experience. In addition, we will ask some of them to prepare material
concrete examples for discussions.


 Helmut Horacek Univ. of the Saarland
 Nicolas Nicolov IBM T.J. Watson Research Center
 Leo Wanner Univ. of Stuttgart


 John Bateman Univ. of Bremen
 Dan Cristea Univ. of Iasi
 Robert Dale Macquarie University
 Laurence Danlos Universite Paris 7
 Marc Dymetman Xerox Research Centre Europe, Grenoble
 Michael Elhadad Ben-Gurion Univ.
 Kristiina Jokinen Univ. of Art and Design Helsinki
 Richard Kittredge Univ. of Montreal & CoGenTex
 Daniel Marcu ISI, Univ. of Southern California
 Chris Mellish Univ. of Edinburgh
 Sergei Nirenburg CRL, New Mexico
 Owen Rambow AT&T Research
 Ehud Reiter Univ. of Aberdeen
 Manfred Stede Technical University of Berlin
 Michael Zock LIMSI, CNRS

SUBMISSIONS (papers, posters, demos)

Papers describing original work in the area of NLG in particular related to
the workshop focus topics above should be submitted electronically. Papers
should be 6-8 pages long in PDF format. We recommend a A4, two-column
format like the ACL proceedings:

We also invite poster and demo submissions (free format, up to 6 page, PDF).

The submissions should be associated with a cover email containing the
following information (ASCII text):

 # TITLE: <title of the paper>
 # AUTHORS: <list of authors>
 # EMAIL: <email of author(s) for correspondence>
 # KEYWORDS: <keywords, topic sub-areas, ...>
 # TYPE: <paper> / <poster> / <demo>
 # ABSTRACT: <abstract of the paper>

Send your submission to Helmut Horacek <>.


 Paper submissions *** 22 April 2001 ***
 Notification of acceptance 6 May 2001
 Camera-ready copies due 16 May 2001
 Registration deadline as ACL
 Workshop dates 6-7 July 2001


The registration fee for the workshop will be posted at a later stage. The
registration fee includes attendance of the workshop and a copy of workshop
proceedings. Follow the registration instructions at the ACL site and
indicate that you would like to attend the NLG workshop.

People wishing to attend the workshop but not submitting papers should send
a notification of attendance: a 1-2 page stating interest to participate,
work done in NLG so far, and potential contributions / material for
discussions about one of the topics. This informationn will help with the
organisation of discussions and allow for an informal and highly
interactive character of the workshop. Notifications of attendance should
be sent to Leo Wanner <>.


 Check the following web site for updates about the NLG workshop:
- -----------------------------------------------------------------------
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue