Main Page
From WikiAI08
Contents |
[edit] Workshop 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 this workshop is to foster the research and dissemination of ideas on the mutually beneficial interaction between Wikipedia and AI. Consistent with the original aim of the workshop, the accepted papers address a highly diverse set of problems, in which Wikipedia is seen either as a useful resource, or as a target for algorithms seeking to make it even better. As a rich knowledge source, Wikipedia is shown to benefit applications in information extraction, machine translation, summarization, ontology mining and mapping, and information retrieval. We also learn of interesting applications, most of them using machine learning, that could further enhance the breadth and the quality of Wikipedia, such as predicting the quality of edits, vandalism detection, infobox extraction, crosslingual links creation, and semantic annotation.
[edit] Venue
The workshop will be held on Sunday, July 13 2008, from 9am until 6pm, at the Hyatt Regency McCormick Place in Chicago. See also the AAAI 2008 sponsored workshops website (W15).
[edit] Registration
To register for the workshop, follow the directions at the AAAI 2008 registration website
[edit] Schedule
The schedule is now available in pdf.
[edit] Invited talk
The workshop will feature an invited talk by Dr. Michael Witbrock, Vice President of Research at Cycorp.
[edit] Acknowledgements
The workshop was made possible through a generous gift from Yahoo! Research.