<html>
<font face="Courier New, Courier">********************** NEW DEADLINE:
25</font><font face="Courier New, Courier" size=1><sup>th</sup></font><font face="Courier New, Courier">
of February 2002 **************<br><br>
<br>
LREC 2002 Workshop on<br><br>
LINGUISTIC KNOWLEDGE ACQUISITION AND REPRESENTATION:<br>
BOOTSTRAPPING ANNOTATED LANGUAGE DATA<br><br>
Las Palmas, Canary Islands, Spain<br><br>
2nd June 2002<br><br>
<br>
********************** NEW DEADLINE:
25</font><font face="Courier New, Courier" size=1><sup>th</sup></font><font face="Courier New, Courier">
of February 2002 **************<br><br>
_____________________________<br><br>
MOTIVATION AND AIMS<br><br>
Provision of large-scale labelled language resources, such as tagged
corpora or repositories of pre-classified text documents, is a crucial
key to steady progress in an extremely wide spectrum of research,
technological and business areas in the HLT sector. The continuously
changing demands for language-specific and application-dependent
annotated data (e.g. at the syntactic or at the semantic level),
indispensable for design validation and efficient software prototyping,
however, are daily confronted by the labelled-data bottleneck.
Hand-crafted resources are often too costly and time-consuming to be
produced at a sustainable pace, and, in some cases, they even exceed the
limits of human conscious awareness and descriptive capability.<br><br>
Possible ways to circumvent, or at least minimise, this problem come from
the literature on automatic knowledge acquisition and, more generally,
from the machine-learning community. Annotated data are bootstrapped by
training a machine-learning classifier with a small sample of
pre-annotated data and by using the induced classifier to annotate more
data. Co-learning provides an alternative methodology, which essentially
consists in iterative cooperation of two or more independent learning
systems. Another promising route consists in automatically tracking down
recurrent knowledge patterns in unstructured or implicit information
sources (such as free texts or machine readable dictionaries) for this
information to be moulded into explicit representation structures (e.g.
subcategorisation frames, syntactic-semantic templates, ontology
hierarchies etc.). <br><br>
We believe that all these attempts at bootstrapping labelled data are not
only of practical interest (for continuous updating, management and
validation of dynamic resources), but also point to a bunch of germane
theoretical issues. In particular, the workshop intends to focus on the
issue of interaction between techniques for inducing structured knowledge
from raw data and formal methods of linguistic knowledge representation.
Gaining insights into this issue is an essential requirement for
explaining the effective use of linguistic knowledge by cognitive agents.
Although the cognitive and engineering views of the form and acquisition
of linguistic knowledge need not be related, data from neuroscience and
psychology are indeed relevant when evaluating different ways of
representing information in artificial systems, and different models for
linguistic knowledge acquisition.<br><br>
We encourage in-depth analysis of underlying assumptions of the proposed
bootstrapping methods and discussion of possible relevant connections
with existing annotation and representation schemes. This investigation
is likely to have significant repercussions on the way linguistic
resources will be designed, developed and used for applications in the
years to come. As the two aspects of knowledge representation and
acquisition are profoundly interrelated, progress on both fronts can only
be achieved, in our view of things, through a full appreciation of this
deep interdependency. <br><br>
<br>
TOPICS OF INTEREST<br><br>
Possible themes for contributions are:<br>
* development of 'data-driven' annotation/representation
schemes<br>
* dynamic update, customisation and tuning of labelled resources through
acquired data<br>
* 'hybrid models' of linguistic knowledge extraction, whereby machine
learning methods are integrated with formal structures of knowledge
representation<br>
* incremental linguistic knowledge-bases<br>
* formal representation and structuring of information flow automatically
acquired from texts<br>
* knowledge acquisition and linguistic resources lifecycle<br>
* linguistic knowledge acquisition and representation in cognitive
tasks<br><br>
<br>
NEW!!! IMPORTANT DATES NEW!!!<br><br>
Deadline for workshop abstract submission:<br>
25th of February 2002<br><br>
Notification of acceptance:<br>
20th of March 2002<br><br>
Final version of paper for workshop proceedings:<br>
20th of April 2002<br><br>
Workshop:<br>
2nd June 2002 (afternoon session)<br><br>
<br>
SUBMISSIONS<br><br>
The organizers welcome contributions describing existing research related
to the topics of the workshop. Each presentation will be 25 minutes long
(20 minutes for presentation and 5 minutes for questions and discussion).
Submissions should include: title; author(s); affiliation(s); and contact
author's e-mail address, postal address, telephone and fax numbers.
Abstracts (maximum 500 words, plain-text format) must be sent to:
simo@ilc.pi.cnr.it<br><br>
The final version of the accepted papers should not be longer than 4,000
words or 10 A4 pages. Instructions for formatting and presentation of the
final version will be sent to authors upon notification of
acceptance.<br><br>
<br>
ORGANISING COMMITEE<br><br>
Alessandro Lenci (Università di Pisa, Italy)<br>
Simonetta Montemagni (Istituto di Linguistica Computazionale - CNR,
Italy)<br>
Vito Pirrelli (Istituto di Linguistica Computazionale - CNR,
Italy)<br><br>
<br>
PROGRAM COMMITTEE <br><br>
Harald Baayen (Max Planck Institute for Psycholinguistics - Nijmegen, The
Netherlands)<br>
Rens Bod (University of Amsterdam, Holland)<br>
Michael R. Brent (Washington University, USA)<br>
Nicoletta Calzolari (Istituto di Linguistica Computazionale - CNR,
Italy)<br>
Jean-Pierre Chanod (Xerox Research Centre Europe, Grenoble, France)<br>
Walter Daelemans (University of Antwerp, Belgium)<br>
Dekang Lin (University of Alberta, Edmonton, Canada)<br>
Horacio Rodriguez (Universidad Politecnica de Catalunya)<br>
Fabrizio Sebastiani (Istituto per l'Elaborazione dell'Informazione - CNR,
Italy)<br>
Lucy Vanderwende (Microsoft Research, Redmond, USA)<br>
François Yvon (Ecole Nationale Superieure des Telecommunications, Paris
Frances)<br>
Menno van Zaanen (University of Amsterdam, The Netherlands) <br><br>
<br>
CONTACT PERSON<br><br>
Simonetta Montemagni<br>
Istituto di Linguistica Computazionale (ILC) - CNR <br>
Area della Ricerca di Pisa <br>
Via Moruzzi 1, 56124 Pisa, ITALY<br>
e-mail: simo@ilc.pi.cnr.it <br><br>
<br>
</font></div>
</html>