INEX 2002 - 2006: understanding XML retrieval evaluation

Abstract

Evaluating the effectiveness of XML retrieval requires building test collections where the evaluation paradigms are provided according to criteria that take into account structural aspects. The INitiative for the Evaluation of XML retrieval (INEX) was set up in 2002, and aimed to establish an infrastructure and to provide means, in the form of large test collections and appropriate scoring methods, for evaluating the effectiveness of content-oriented XML retrieval. This paper describes the evaluation methodology developed in INEX, with particular focus on how evaluation metrics and the notion of relevance are treated. © Springer-Verlag Berlin Heidelberg 2007.