|
|
|
                                          
|
Return to Session IIa: Test collections
This paper examines whether the Cranfield evaluation methodology is robust to gross violations of the completeness assumption (i.e., the assumption that all relevant documents within a test collection have been identified and are present in the collection). We show that current evaluation measures are not robust to substantially incomplete relevance judgments. A new measure is introduced that is both highly correlated with existing measures when complete judgments are available and more robust to incomplete judgment sets. This finding suggests that substantially larger or dynamic test collections built using current pooling practices should be viable laboratory tools, despite the fact that the relevance information will be incomplete and imperfect.
@inproceedings{1009000, author = {Chris Buckley and Ellen M. Voorhees}, title = {Retrieval evaluation with incomplete information}, booktitle = {SIGIR '04: Proceedings of the 27th annual international conference on Research and development in information retrieval}, year = {2004}, isbn = {1-58113-881-4}, pages = {25--32}, location = {Sheffield, United Kingdom}, doi = {http://doi.acm.org/10.1145/1008992.1009000}, publisher = {ACM Press}, }  ©2005 Association for Computing Machinery |
