A Renewed Matrix Model for XML Data

We start with a convenient vector space model and extend it with information about structural properties of an XML data collection C. We represent t by a vector of weights on paths in C, since a path is a structure unit in C. An XML document D is represented by a matrix D of weights. We discuss possibilities of ranking in this model and adjusting D to reflect associations among paths in C. The original matrix model is extended using term weighting in a context in the paper. There were done several experiments with data from the INEX collection using new version of matrix model, which justified its existence, particularly for queries with more terms.