|
home
>> program >> Workshops
WORKSHOPS
WS1: CoNLL-2003: Seventh Conference on Natural Language Learning
Saturday and Sunday May 31 and June 1, 2003
http://cnts.uia.ac.be/conll2003/
Submission due date: March 16
CoNLL is an international forum for discussion and presentation
of research on natural language learning. We invite submission
of papers about natural language learning topics, including but
not limited to: computational models of human language acquisition;
computational models of the origins and evolution of language;
machine learning methods applied to natural language processing
tasks (speech processing, phonology, morphology, syntax, semantics,
discourse processing, language engineering applications); symbolic
learning methods (Rule Induction and Decision Tree Learning, Lazy
Learning, Inductive Logic Programming, Analytical Learning, Transformation-based
Error-driven Learning); biologically-inspired methods (Neural
Networks, Evolutionary Computing); statistical methods (Bayesian
Learning, HMM, maximum entropy, SNoW, Support Vector Machines);
Reinforcement Learning; Active learning, ensemble methods, meta-learning;
Computational Learning Theory analysis of language learning; empirical
and theoretical comparisons of language learning methods; models
of induction and analogy in Linguistics. As in previous editions,
CoNLL-03 will feature an invited speaker, a shared task (named-entity
recognition) and a special theme (semi-supervised, unsupervised
and sample selection techniques for language learning).
WS2: DUC03: Text Summarization Workshop
Saturday and Sunday May 31 and June 1, 2003
http://www.umich.edu/cl/hlt-naacl-duc03/
Submission due date: February 28
Over the last three years, the DUC series (Document Understanding
Conference, http://duc.nist.gov/)
has been the main forum for Research and evaluation of text summarization.
The workshop requests papers on all aspects of text summarization,
including but not limited to: non-extractive summarization, spoken
language (including dialogue) summarization, language modeling
for text and speech summarization, multi-document and multilingual
summarization, integration of question answering and summarization,
Web-based summarization, evaluation of summarization systems,
etc. The second day of the workshop will be devoted to discussing
the results of the DUC 2003 evaluation, administered by NIST,
that took place in mid-February.
WS3: Research Directions in Dialogue Processing
Saturday and Sunday May 31 and June 1, 2003
http://www.speech.cs.cmu.edu/hltnaacl2003/
Submission due date: March 21
This workshop will provide a forum for discussion of current directions
in dialog research, specifically to assess the current state of
the art in the area of dialogue processing, and to identify key
themes and directions that are driving research in the field.
Progress in research presupposes the existence of a common infrastructure
that includes tools and corpora, evaluation techniques as well
as some consensus on effective research paradigms. Thus one of
the outcomes of the workshop will be a set of recommendations
for developing and supporting infrastructure, and encouraging
agreement on research paradigms and evaluation methodologies.
The motivation to hold a workshop at this time is the need to
establish the role of dialogue as a core element in human-human
and human-computer communication, to identify the resources that
are needed to support research in the area and to define its role
in the forthcoming NSF Human Language and Communication program.
WS4: Building and Using Parallel Texts: Data Driven Machine
Translation and Beyond
Saturday May 31, 2003
http://www.cs.unt.edu/~rada/wpt
Submission due date: Full papers: March 10 (regular
papers) / April 1 (short papers)
This workshop provides a forum for researchers working on problems
related to building and using parallel text corpora, which are
vital resources for efficiently deriving multi-lingual text processing
tools. In addition to regular papers, the workshop also includes
a shared task that will result in a comparative evaluation of
word alignment techniques. We invite submissions of papers addressing
any of the following issues, with work addressing languages with
scarce resources being particularly welcome: constructing parallel
corpora, including the automatic identification and harvesting
of parallel corpora from the Web; evaluating the quality of parallel
corpora and word alignments; tools for processing parallel corpora,
including automatic sentence alignment, word alignment, phrase
alignment, detection of omissions and gaps in translations, and
others; using parallel corpora for data driven Machine Translation;
using parallel corpora for the derivation of language processing
tools in new languages; using parallel corpora for automatic annotation;
language learning applied to parallel corpora; translation memory
systems as a source of aligned corpora. The invited speaker will
be Elliott Macklovitch from the University of Montreal.
WS5: Software Engineering and Architecture of Language Technology
Systems (SEALTS)
Saturday May 31, 2003
http://www.it.usyd.edu.au/research/sealts.html
Submission due date: March 23
Over the past few years a number of significant systems and practices
have been developed in what may be called Software Architecture
for Language Engineering. Among the most prominent are: RAGS,
Reference Architecture for Generation Systems (Brighton and Edinburgh)
LT XML (Edinburgh) TEI, CES, XCES (Oxford, Vassar, etc.) ATLAS
(LDC, NIST) Galaxy Communicator Software Infrastructure (MIT &
MITRE) Protege (Stanford) GATE, a General Architecture for Text
Engineering (Sheffield) This workshop represents an opportunity
to discuss in a coordinated setting the advances and problems
of computational infrastructure and architectures for large-scale
and robust Natural Language Processing systems.
WS6: Text Meaning
Saturday May 31, 2003
http://www.research.umbc.edu/~sergei/
Submission due date: March 17
Most, if not all, high-end HLT/NLP applications - from the earliest,
MT, to the latest, question answering and text summarization -
stand to benefit from being able to use text meaning in their
processing. But the bulk of work in the field has not, over the
years, pertained to treatment of meaning. The main reason given
is the complexity of the task of comprehensive meaning analysis.
The principal goal of this workshop is to re-establish the research
community of knowledge-based meaning processing and to help to
explicate the currently implicit treatments of meaning in knowledge-lean
approaches and how the advances in the latter and in formal semantics
should influence the task. Please submit papers (not to exceed
8 pages in the HLT/NAACL two-column format) electronically, PDF
strongly preferred, to sergei@umbc.edu.
WS7: Building Educational Applications Using Natural Language
Processing
Saturday May 31, 2003
http://www.etstechnologies.com/NAACL
Submission due date: March 17 (note new deadline)
There is an increased use of HLT-based educational applications
for both large-scale assessment and classroom instruction. This
has occurred for two primary reasons. First, there has been a
significant increase in the availability of computers in schools,
from elementary school to the university. Second, there has been
notable development in computer-based educational applications
that incorporate advanced methods in HLT that can be used to evaluate
students' work. Educational applications have been developed across
a variety of subject domains in automated evaluation of free-responses
and intelligent tutoring. To date, these two research areas have
remained autonomous. We hope that this workshop will facilitate
communication between researchers who work on all types of instructional
applications, for K-12, undergraduate, and graduate school. Since
most of this work in HLT-based educational applications is text-based,
we are especially interested in any work of this type that incorporates
speech processing and other input/output modalities. We wish to
expose the NLP research community to these technologies with the
hope that they may see novel opportunities for use of their tools
in an educational application.
WS8: Learning Word Meaning from Non-Linguistic Data
Saturday May 31, 2003
http://www.cs.cornell.edu/~regina/lwm03/
Submission due date: March 10
One of the grand challenges of NLP, AI, and Cognitive Science
is to develop models of what words mean (lexical semantics) in
terms of the non-linguistic world. Recently there has been growing
interest in using corpus and data based techniques for this task.
In other words, trying to learn what words mean by analysing a
'parallel corpus' of (A) non-linguistic data and (B) linguistic
texts that describe or otherwise are based on the non-linguistic
data. Recent examples of such work include learning verb semantics
from visual-image sequences; learning the meaning of time phrases
from a collection of weather forecasts based on numerical weather
simulations; and learning the meaning of mathematical predicates
from human verbalisations of theorem-prover output. We hope that
this workshop will help "gel" this new and exciting research area,
by bringing together interested people who may not be aware of
what is being done elsewhere. Participants from other area of
AI and Cognitive Science are very welcome, including vision and
robotics researchers who are interested in learning how to relate
sensor data to words, and psychologists who are interested in
cognitive models of how people learn to relate words to the non-linguistic
world.
WS9: Analysis of Geographic References
Saturday May 31, 2003
http://www.kornai.com/NAACL
Submission due date: March 15
This workshop will discuss how existing NLP techniques can be
adapted and new ones developed to advance core technology in geographic
reference analysis. Two-page extended abstracts are due March
15 (electronic submissions only, please, mailed to geowkshp@kornai.com).
Student Workshop
Date to be determined
http://www.cs.cornell.edu/~ebreck/hlt-naacl03-student/
Submission due date: March 15
The Student Research Workshop, a tradition at ACL conferences,
is being expanded to include also students from the Information
Retrieval and Speech communities. Participants will have the opportunity
to get feedback both from a wide audience in general and from
selected panelists: experienced researchers who prepare in-depth
comments and questions in advance of the presentation. We invite
student researchers to submit their work to the workshop. The
emphasis will be on work in progress. Original and unpublished
research is invited on all aspects of speech, information retrieval,
and computational linguistics. We especially encourage research
that is in the intersection of two or three of these areas, or
that fall in the primary workshop topics:
- Language modeling
- Topic detection
- Information extraction
Additional topics of interest: Dialog systems and spoken language
understanding, Speech synthesis and natural language generation,
Speech-to-speech translation, Spoken document retrieval, Prosody
and parsing, Question answering, Summarization and gisting, User
modeling and adaptation, Disambiguation, stemming, lexical chains.
|