|
Third International Workshop on
Scalable Natural Language Understanding
(ScaNaLU 2006)
June 8, 2006, following HLT/NAACL, New York City
There is a growing need for systems that can
understand and generate natural language in applications that require
substantial amounts of knowledge as well as reasoning capabilities.
Most current implemented systems for natural language understanding
(NLU) are decoupled from any reasoning processes, which makes them
narrow and brittle. Furthermore, they do not appear to be scalable in
the sense that the techniques used in such systems do not appear to
generalize to more complex applications. While significant work has
been done in developing theoretical underpinnings of systems that use
knowledge and reasoning (e.g., development of models of linguistic
interpretation using abductive reasoning, intention recognition, formal
models of dialogue, formal models of lexical and utterance meaning, and
utterance planning), it has often proved difficult to utilize such
theories in robust working systems.
Another major barrier has been the vast amount of
linguistic and world knowledge needed. But there is now significant
progress in compiling and learning the required knowledge, using
manual, statistical and hybrid techniques. But even as these resources
become available, we still lack some key conceptual and computational
frameworks that will form the foundation for effective scalable natural
language systems.
There are many applications that would be enabled or
benefit greatly from scalable language systems, including, the design
of smart user interfaces that act more as a personal assistant than a
computer, intelligent tutoring systems that can fully engage the
student in responsive interaction, machine translation systems, text
and message understanding, and natural language interfaces to knowledge
management systems that move beyond data based queries to enable
planning, situational analysis, and other “cognitive” capabilities.
FORMAT FOR SUBMISSION:
The format and length requirements will be the same
as for full papers of NAACL/HLT 2006, except that submission will not
be blind. See http://nlp.cs.nyu.edu/hlt-naacl06/styles/index.html for
details.
SUBMISSION PROCEDURE:
Papers should be sent to
robert.porzel@eml-d.villa-bosch.de. The paper should be an attachment
in PDF format and the heading on the email should read "PAPER
SUBMISSION". Notification of acceptance or rejection will be sent to
the originating email address.
LANGUAGE: all papers must be written and presented in English
IMPORTANT DATES:
Papers due: March 31th, 2006
Acceptance/rejection notification: April 24th, 2006
Final version due: May 8th, 2006
Workshop: June 8, 2006
ORGANIZING COMMITTEE:
James Allen, University of Rochester
Jan Alexandersson, DFKI Saarbrücken
Jerry Feldman, University of Berkeley
Robert Porzel, EML, Heidelberg
PROGRAM COMMITTEE
Berenike Loos, EML, Heidelberg
Dan Gildea, University of Rochester
Günther Görz, University of Erlangen
Hans Uszkoreit, Saarland University
Len Schubert, University of Rochester
Stanley Peters, Stanford University
Tilman Becker, DFKI GmbH
Paul Buitelaar, DFKI GmbH
Dan Flickinger, Oslo, Saarland and Stanford Universities
Tomasz Marciniak, Language Computer Corporation, Richardson, Texas
Vanessa Micelli, EML, Heidelberg
Massimo Poesio, University of Essex
Aldo Gangemi, Laboratory for Applied Ontology, Rome
Joachim De Beule, University of Brussels
Hans-Peter Zorn, EML, Heidelberg
Rainer Malaka, University of Bremen
SCOPE/AUDIENCE
The workshop aims
at bringing together researchers involved using knowledge
representations and reasoning systems to support language understanding
and generation. The goal is to find common ground and exchange ideas in
the fields of ontology, grammar, semantics, representation, reasoning,
and pragmatics, etc. in order to strengthen individual approaches and
combine modeling efforts.
In the ScaNaLU
2006 workshop we intend to bring together researchers working in
various sub-fields of natural language understanding with an interest
in building scalable systems. The scope of interest includes but is not
limited to:
- Integrating hybrid approaches combining knowledge-based and statistical approaches
- Multi-modal interfaces including language understanding in knowledge-rich domains
- Natural Language Generation: From sentences to extended discourse
- Utilization of world knowledge into NLU systems
- Semantic formalisms and grammars for scalable NLU
-
Knowledge-driven discourse models of NLU (e.g., speech act
interpretation, implicature, intention recognition, reference resolution
- Representation standards
- Integration of extra-linguistic and pragmatic contexts
- (Semi-)automatic acquisition of linguistic and world knowledge
- Theories of semantic and pragmatic phenomena (e.g., metonymy, metaphor, degree expressions)
- Applications requiring deep semantic analysis and reasoning
WORKSHOP FORMAT AND SCHEDULE:
The workshop will
interleave technical presentations with extensive time or discussion of
the presented work. Before the workshop we will assign a commentator
for each accepted presentation from the attendees, in order to kick off
a lively discussion. Altogether the format will consist of four
elements:
- Paper presentations with commentators and discussion
- Invited talk(s)
- Application and device demonstrations with discussion
- Panel discussion
We will accept
paper submissions for both technical presentations and demonstrations.
We plan to be reasonably selective in order to have a high quality
workshop. The papers will be published in workshop proceedings and we
will try to forward the best ones to some high quality journal.
|
