AAAI 2008 Workshop
WIKIPEDIA AND ARTIFICIAL INTELLIGENCE: AN EVOLVING
SYNERGY
http://lit.csci.unt.edu/~wikiai08
CALL FOR PAPERS
OVERVIEW
Since its inception less than seven years ago, Wikipedia has become one of the
largest and fastest
growing online sources of encyclopedic knowledge. One of the reasons why
Wikipedia is
appealing to contributors and users alike is the richness of its embedded
structural information:
articles are hyperlinked to each other and connected to categories from an ever
expanding
taxonomy; pervasive language phenomena such as synonymy and polysemy are
addressed
through redirection and disambiguation pages; entities of the same type are
described in a
consistent format using infoboxes; related articles are grouped together in
series templates.
As a large-scale repository of structured knowledge, Wikipedia has become a
valuable resource
for a diverse set of Artificial Intelligence (AI) applications. Major
conferences in natural language
processing and machine learning have recently witnessed a significant number of
approaches that
use Wikipedia for tasks ranging from text categorization and clustering to word
sense
disambiguation, information retrieval, information extraction and question
answering. On the
other hand, Wikipedia can greatly benefit from numerous algorithms and
representation models
developed during decades of AI research, as illustrated recently in tasks such
as estimating the
reliability of authors' contributions, automatic linking of articles, or
intelligent matching of
Wikipedia tasks with potential contributors.
The goal of the workshop is to foster the research and dissemination of ideas on
the mutually
beneficial interaction between Wikipedia and AI. The workshop is intended to be
highly
interdisciplinary. We encourage participation of researchers working on
Wikipedia from different
perspectives, including (but not limited to) machine learning, computational
linguistics,
information retrieval, information extraction, question answering, knowledge
representation, and
others. We also encourage participation of researchers from other areas who
might benefit from
the use of a large body of machine-readable knowledge.
TOPICS
We invite submissions of papers addressing the following or related topics::
- Using Wikipedia as a source of training data for AI tasks (both supervised an
unsupervised)
- Automatic methods for improving the quality of Wikipedia pages
- Integrating Wikipedia with existing ontologies (e.g. WordNet, CYC, ODP)
- Extracting annotated data from Wikipedia
- Enriching Wikipedia with new types of structural information
- Wikipedia and the Semantic Web / Web 2.0
- Automatic extraction and use of cross-lingual information from Wikipedia
- Computerized use of satellite projects such as Wiktionary, Wikibooks or
Wikispecies
WORKSHOP FORMAT
The day long workshop will consist of presentations, demos showcasing work
presented in
the research papers, and a panel session. The workshop will also feature an
invited talk by
Dr. Michael Witbrock, Vice President of Research at Cycorp, where he works on
the Cyc project.
SUBMISSION GUIDELINES
We invite submissions of regular full papers (up to 6 pages), short papers
reporting on late-
breaking results (up to 3 pages), and descriptions of system demonstrations (up
to 1 page) using
the AAAI style. Submissions that have been accepted for publication elsewhere or
are under
review for another conference must clearly state so on the front page of the
paper.
IMPORTANT DATES
Deadline for long papers submission March 21, 2008
Deadline for short papers and system demos April 7, 2008
Notification of acceptance April 21, 2008
Camera-ready papers due at AAAI May 5, 2008
ORGANIZING COMMITTEE
Razvan Bunescu, Ohio University (bunescu(a)ohio.edu)
Evgeniy Gabrilovich, Yahoo! Research (gabr(a)yahoo-inc.com)
Rada Mihalcea, University of North Texas (rada(a)cs.unt.edu)
PROGRAM COMMITTEE
1. Eugene Agichtein, Emory University
2. Einat Amitay, IBM Research, Israel
3. Mikhail Bilenko, Microsoft Research
4. Chris Brew, Ohio State University
5. Timothy Chklovski, Structured Commons
6. Massimiliano Ciaramita, Yahoo! Research Barcelona, Spain
7. Andras Csomai, University of North Texas
8. Silviu Cucerzan, Microsoft Research
9. Ido Dagan, Bar-Ilan University, Israel
10. Ravi Kumar, Yahoo! Research
11. Lillian Lee, Cornell University
12. Elizabeth Liddy, Syracuse University
13. Daniel Marcu, Information Sciences Institute, University of Southern
California
14. Shaul Markovitch, Technion, Israel
15. Raymond Mooney, University of Texas at Austin
16. Vivi Nastase, EML Research, Germany
17. Marius Pasca, Google
18. Ted Pedersen, University of Minnesota, Duluth
19. Simone Paolo Ponzetto, EML Research, Germany
20. Dragomir Radev, University of Michigan
21. Dan Roth, University of Illinois Urbana-Champaign
22. Peter Turney, National Research Council, Canada
ADDITIONAL INFORMATION
For additional information about the workshop please contact the organizers or
visit the
workshop website at
http://lit.csci.unt.edu/~wikiai08