Retrieval Evaluation with Incomplete Information

Published

July 1, 2004

Author(s)

C E. Buckley, Ellen M. Voorhees

Abstract

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.

Proceedings Title

Proceedings of the Twenty-Seventh Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Sheffield, UK, July 2004

Conference Dates

July 1, 2004

Conference Location

Sheffield, 1, UK

Conference Title

ACM Special Interest Group in Information Retrieval (SIGIR)

Pub Type

Conferences

Download Paper

Local Download

Keywords

evaluation, information retrieval, test collections

Citation

Buckley, C. and Voorhees, E. (2004), Retrieval Evaluation with Incomplete Information, Proceedings of the Twenty-Seventh Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Sheffield, UK, July 2004, Sheffield, 1, UK, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=150469 (Accessed April 18, 2024)