We consider the problem of eliminating redundant Boolean features for a given data set, where a feature is redundant if it separates the classes less well than another feature or set of features. Lavrač et al. proposed the algorithm REDUCE that works by pairwise comparison of features, i.e., it eliminates a feature if it is redundant with respect to another feature. Their algorithm operates in an ILP setting and is restricted to two-class problems. In this paper we improve their method and extend it to multiple classes. Central to our approach is the notion of a neighbourhood of examples: a set of examples of the same class where the number of different features between examples is relatively small. Redundant features are eliminated by applying a revised version of the REDUCE method to each pair of neighbourhoods of different class. We analyse the performance of our method on a range of data sets.

We describe an initiative under way at Warwick to provide a technical foundation for computer-aided learning and computer-assisted assessment tools, which allows a rich dialogue sensitive to individual students' response patterns. The system distinguishes between dialogues for individual problems and the linking of problems. This enables a subject specialist to craft individual questions and units of learning material, while allowing the order of presentation of the units to depend on a student's interaction history. We develop a markup language, specified as an XML DTD, to enable the storage of data for use in such systems.