DEADLINE EXTENSION: ESSLLI'01 Workshop on Semantic Knowledge Acquisition and Categorisation (Helsinki, Finland)

Ahti Pietarinen [email protected]
Thu, 15 Mar 2001 18:56:09 +0200 (EET)


*************** EXTENDED DEADLINE ****************

----- NEW DEADLINE: APRIL 23rd -----

----- Please check new dates below! -----


SEMANTIC KNOWLEDGE ACQUISITION AND CATEGORISATION

Workshop at ESSLLI XIII (Helsinki, Finland)

Helsinki, Finland, August 13th - 17th 2001

Workshop home page
http://www.ilc.pi.cnr.it/~esslli

ESSLLI 2001 home page
http://www.helsinki.fi/esslli

-------------------------------------------------------------------

Endorsed by SIGSEM, the ACL Special Interest Group on computational
semantics

-------------------------------------------------------------------

The sheer amount of knowledge necessary to shed light on the way word
meanings mutually relate in context or distribute in lexico-semantic
classes appears to exceed the limits of human conscious awareness and
descriptive capability. Particularly at this level of linguistic analysis,
then, we seem to be in need of automatic ways of filtering, structuring
and classifying semantic evidence through inspection of a large number of
word uses in context. Totally or partially unsupervised inductive methods
of knowledge acquisition from corpus data are credited with being able to
provide such ways. Yet, it remains to be seen how acquired information can
best be represented in current formal models for knowledge representation,
for it to be made available to mainstream NLP applications.

There are reasons to believe that this integration will require much more
than a simple extension of off-the-shelf machine learning technology. At
the same time, any major breakthrough in this area is bound to have
significant repercussions on the way word meanings and lexico-semantic
classes in general are formally represented and used for applications.
With these purposes in mind, the workshop intends to focus on the issue of
interaction between techniques for inducing semantic information from
corpus data and formal methods of linguistic knowledge representation. In
particular, we encourage in-depth analysis of underlying assumptions of
the proposed techniques and methods and discussion of possible relevant
connections with cognitive, linguistic,logical and philosophical issues.


TOPICS OF INTEREST

Possible themes for contributions are:

- development of 'data-driven' semantic type systems
- dynamic update and tuning of formal ontologies with text data
- 'hybrid models' of knowledge extraction, whereby machine learning
  methods are integrated with formal structures of knowledge representation
- creation of dynamic lexical knowledge-bases
- formal representation and structuring of the flow of information
  extracted from texts.


WORKSHOP ORGANISATION

The workshop will be held on five subsequent days, August 13th-17th 2001.
It will take place during the ESSLLI-Summer School in Helsinki, and will
be open to all members of the LLI-community, computational linguistics and
cognitive science as well. Each session will consist of two talks plus
discussion (30mins + 15mins each). The workshop language will be English.

----------------------------------------------------------------------------
GUIDELINES FOR SUBMISSIONS

The organizers welcome contributions from different fields of
computational linguistics, logic and cognitive science.

1. Submissions will consist of full papers reporting on original,
   unpublished works. Papers should not exceed 5000 words
   (including references), must contain a 5-10 lines abstract, and must
   be submitted in postscript format

2. The reviewing of papers will be blind. Hence the paper
   should not include the authors' names and affiliations.
   Furthermore, self-references that reveal the author's identity
   should be avoided.

3. Identification information will be put in a separate file
   consisting of:
   Title of the paper:
   Author(s):
   Affiliation(s):
   E-mail(s):
   Abstract:

4. Submitted papers and identification information must be sent
   to the following address by APRIL 23rd 2001:

   [email protected]

Accepted papers will be notified by MAY 15th, together with the comments
of the reviewers.

The final version of the papers will be prepared in LaTeX by JUNE 15th,
for publication in the Workshop proceedings. The stylesheet will be
circulated in due time.

Note that all workshop participants must register as participants of
ESSLLI. The early registration fees apply to authors of accepted papers.

---------------------------------------------------------------------------
IMPORTANT DATES

April  23rd 2001 - Deadline for submitting papers
May    15th 2001 - Notification of acceptance
June   15th 2001 - Preparation of the final version of the paper
June   30th 2001 - Final program of the workshop
August 13th 2001 - The workshop begins
---------------------------------------------------------------------------

PROGRAM COMMITEE

Ted Briscoe (Cambridge University, Cambridge, United Kingdom)
Nicoletta Calzolari (Istituto di Linguistica Computazionale, CNR, Pisa, Italy)
Christiane Fellbaum (Princeton University, Princeton, USA)
Ed Hovy (USC, Marina del Rey CA, USA)
Dekang Lin (University of Alberta, Edmonton, Canada)
Antonio Sanfilippo (LingoMotors Inc., Cambridge MA, USA)
Piek Vossen (SAILLABS, Antwerpen, The Netherlands)


ORGANISING COMMITEE

Alessandro Lenci
Simonetta Montemagni
Vito Pirrelli

Istituto di Linguistica Computazionale (ILC) - CNR
Area della Ricerca CNR
Via Alfieri 1 (San Cataldo)
I-56010 PISA
Italy


WORKSHOP CONTACT ADDRESS

[email protected]
http://www.ilc.pi.cnr.it/~esslli

ESSLLI 2001 CONTACT ADDRESS

[email protected]
http://www.helsinki.fi/esslli

--------------------------------------------------------------------------