|SIGIR 2009 Workshop||July 23, 2009|
Redundancy, Diversity, and
Interdependent Document Relevance (IDR '09)
This workshop will explore how ranking, performance assessment, and learning to rank can move beyond the assumption that the relevance of documents in a ranking is independent. The focus will be on three key themes: the effect of redundancy on information retrieval utility (e.g. how to measure redundancy, avoid it in evaluation and when training ranking algorithms); the role of diversity (e.g. for mitigating the risk of misinterpreting ambiguous queries); approaches to set-level evaluation and optimization (e.g. how to create reusable set-level judgments that trade off between evaluating relevance relative to the needs of a specific user versus the needs of a distribution of users).
Oct. 19, 2009: A summary of the workshop, to appear in SIGIR Forum, is now available. Thanks again to all the speakers, participants, and PC members for making it a great workshop!
Paul N. Bennett, Microsoft Research
Ben Carterette, University of Delaware
Thorsten Joachims, Cornell University
Filip Radlinski, Microsoft Research
Contact: Filip Radlinski and Ben Carterette
|June 2, 2009||Submission deadline|
|June 18, 2009||Notification of acceptance|
|July 7, 2009||Camera-ready submission|
|July 23, 2009||Workshop in Boston|