Abstract
Standard Information RetrievalĀ (IR) metrics are not well suited for new paradigms like XML IR in which retrievable information units are document elements. These units are neither predefined nor independent, and the elements returned by IR systems may overlap and contain near misses. Part of the problem stems from the classical hypotheses on the user behaviour that do not take into account the structural or logical context of document elements or the possibility of navigation between retrievable units. The Expected Precision Recall with User ModelĀ (EPRUM) metric is based on a more realistic user model which encompasses a large variety of user behaviours. In this paper, we present the EPRUM metric used for evaluating the official submissions of INEX 2005 and detail the settings we used. We do not present the full derivation of the EPRUM metric but we give a thorough example of its computation along with the complete set of formulas needed to compute precision at different recall values. We also discuss the implication of such a metric on several key problems of XML Information Retrieval as the notion of the ideal list and the problem of the overlap.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cooper, W.S.: Some inconsistencies and misidentified modelling assumptions in probabilistic information retrieval. In: Belkin, N.J., Ingwersen, P., Pej, A.M. (eds.) Proceedings of the 14th ACM SIGIR, Copenhagen, Danemark. ACM Press, New York (1992)
Kazai, G., Lalmas, M.: Notes on what to measure in inex. In: Ā Trotman, A., Lalmas, M., Fuhr, N. (eds.) Proceedings of the INEX 2005 Workshop on Element Retrieval Methodology. University of Otago, Univerisity of Glasgow, Information Retrieval Festival (2005)
Piwowarski, B., Gallinari, P.: Expected ratio of relevant units: A measure for structured information retrieval. In: Fuhr, N., Lalmas, M., Malik, S. (eds.) INitiative for the Evaluation of XML Retrieval (INEX). Proceedings of the Second INEX Workshop, Dagstuhl, France (December 2003)
Piwowarski, B., Gallinari, P., Dupret, G.: An extension of precision-recall with user modelling (PRUM): Application to XML retrieval (2005) (submitted for publication)
Raghavan, V.V., Jung, G.S., Bollmann, P.: A critical investigation of recall and precision as measures of retrieval system performance. ACM Transactions on Information SystemsĀ 7(3), 205ā229 (1989)
Voorhees, E.M.: Common evaluation measures. In: The Twelfth Text Retrieval Conference (TREC 2003), number SP 500-255, NIST, pp. 1ā13 (2003)
Vries, A., Kazai, G., Lalmas, M.: Tolerance to irrelevance: A user-effort oriented evaluation of retrieval systems without predefined retrieval unit. In: Proceedings of RIAO (Recherche dāInformation AssistĆ©e par Ordinateur (Computer Assisted Information Retrieval)), Avignon, France (April 2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Piwowarski, B. (2006). EPRUM Metrics and INEX 2005. In: Fuhr, N., Lalmas, M., Malik, S., Kazai, G. (eds) Advances in XML Information Retrieval and Evaluation. INEX 2005. Lecture Notes in Computer Science, vol 3977. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11766278_3
Download citation
DOI: https://doi.org/10.1007/11766278_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-34962-4
Online ISBN: 978-3-540-34963-1
eBook Packages: Computer ScienceComputer Science (R0)