Donnerstag, 21. April 2011

SIRE 2011–Information Retrieval for E-discovery

Please send replies or questions to Doug Oard (oard@umd.edu)

 

Call for Submissions
SIGIR Workshop on Information Retrieval for E-discovery (SIRE)
July 28, 2011, Beijing, China
http://www.umiacs.umd.edu/~oard/sire11/
 
A workshop held in conjunction with the 2011 
International ACM SIGIR Conference on Research and Development in Information Retrieval

Electronic discovery ("e-discovery") is the use of Information Retrieval (IR) technology to find evidence requested by a party in a legal matter. This application of IR has grown explosively in recent years.  The SIRE workshop will provide a forum for discussion of IR techniques that have or that could be applied to e-discovery, as well as methods for evaluating the effectiveness and cost of such approaches.  Topics of interest include, but are not limited to: 

  • Distributed search of large heterogeneous enterprise information systems, including corporate intranets, archival and backup repositories, cloud-based storage, etc.
  • High-recall search of large collections, including those with high densities of relevant documents
  • Supervised learning of classifiers for responsiveness, privilege and other factors of interest (sometimes referred to in e-discovery as predictive coding)
  • IR techniques that leverage the characteristics of specific types of business records (email, instant messages, voice mail, file systems, etc.)
  • Clustering, link analysis, and other methods for discovering structure in large collections, including detection of duplicate documents
  • Process design for human-in-the-loop review and exploitation of large data sets, including measurement of inter-reviewer consistency, active learning, etc.
  • Evaluation design, including sampling strategies, estimation of confidence intervals, and reusability of large test collections

Submissions: 
 
As we presently conceive the workshop, the first session will lay out the nature of e-discovery, thus making the workshop accessible to SIGIR attendees with no prior e-discovery experience. A keynote talk will be followed by a panel discussion by senior IR and e-discovery experts, with substantial time for audience interaction. The second session will then focus on IR techniques. The third session, after lunch, will focus on evaluation. In both cases, the goal will be to dive deeply into specific issues. For the second and third sessions we envision a "discussant" structure in which the talks will be followed by comments from a discussant who seeks to critique, contrast, and/or provoke.  The fourth session will feature a moderated panel discussion focused on crafting a research agenda. The goal will be to identify key issues, venues for action, communities with which to engage, and support to seek. Two types of written contributions are therefore invited:
 
·         Brief (typically 1-2 page) position papers describing individual interests, for inclusion (without review) on the SIRE Web site and distribution to workshop participants.  Brief descriptions of this type can be particularly valuable for workshop like this one in which we seek to bring together diverse research communities.  Additionally, these papers can help with our selection of discussion leaders, discussants, and panelists.  Position papers are requested by June 3, 2011.  Participation in the workshop is open, so prior submission of position papers is strongly encouraged, but not strictly required.    
 
·         Original research papers (4-10 pages).  After peer review, accepted papers will be posted on the SIRE website and made available in hard-copy to workshop participants.  Authors of accepted research papers will be invited to present their work either as an oral or a poster presentation.  Research papers are due on May 13, 2011; decisions will be returned by June 3, 2011.
 
Submissions should be sent by email to Doug Oard (oard@umd.edu) with the subject line SIRE POSITION PAPER or SIRE RESEARCH PAPER.  All submissions received will be acknowledged within 3 days.    
 
Organizing Committee:
 
Jason R. Baron, National Archives and Records Administration, USA
Maura Grossman, Wachtell, Lipton, Rosen and Katz, USA
Dave Lewis, David D. Lewis Consulting, USA
Douglas W. Oard, University of Maryland, USA