Purpose – Information retrieval (IR) and feedback in Extensible Markup Language (XML) are rather new fields for researchers; natural questions arise, such as: how good are the feedback algorithms in XML IR? Can they be evaluated with standard evaluation tools? Even though some evaluation methods have been proposed in the literature it is still not clear yet which of them are applicable in the context of XML IR, and which metrics they can be combined with to assess the quality of XML retrieval algorithms that use feedback. This paper aims to elaborate on this. Design/methodology/approach – The efficient evaluation of relevance feedback (RF) algorithms for XML collection posed interesting challenges on the IR and database researchers. The system based on the keyword‐based queries whether on the main query or in the RF processing instead of the XPath and structure query languages which were more complex. For measuring the efficiency of the system, the paper used the extended RF algorithms (residual collection and freezeTop) for evaluating the performance of the XML search engines. Compared to previous approaches, the paper aimed at removing the effect of the results for which the system has knowledge about their relevance, and at measuring the improvement on unseen relevant elements. The paper implemented the proposed evaluation methodologies by extending a standard evaluation tool with a module capable of assessing feedback algorithms for a specific set of metrics. Findings – In this paper, the authors create an efficient XML retrieval system that is based on a query refinement by making a feedback processing and extending the main query terms with new terms mostly related to the main terms. Research limitations/implications – The authors are working on more efficient retrieval algorithms to get the top‐ten results related to the submitted query. Moreover, they plan to extend the system to handle complex XPath expression. Originality/value – This paper presents an efficient evaluation of RF algorithms for XML collection retrieval system.
International Journal of Web Information Systems – Emerald Publishing
Published: Jun 22, 2010
Keywords: Extensible Markup Language; Information retrieval; Algorithmic languages