Arabic is the fourth most widely spoken language in the world, and is characterised by a high rate of inflection. To cater for this, most Arabic information retrieval systems incorporate a stemming stage. Most existing Arabic stemmers are derived from English equivalents; however, unlike English, most affixes in Arabic are difficult to discriminate from the core word. Removing incorrectly ident...

A bs t rac t and-egg problem can be solved by using a cooperative computation in a parallel network. The computation performs a parallel, iterative search which settles on both the reference frame and the shape description at the same time. One way to achieve viewpoint-invariant shape recognition is to impose a canonical, object-based frame of reference on a shape and to describe the positions,...

Applying GAC on conjunctions of constraints can lead to more powerful pruning [1]. We show that there exists a simple heuristic for deciding which constraints might be useful to conjoin. The result is a useful automatic way of improving a CSP model for GAC solving.

Selective Tuning (ST) [1] presents a framework for modeling attention and in this paper we show how it performs in visual search tasks. Two types of tasks are presented, a motion search task and an object search task. Both tasks are successfully tested with different feature and conjunction visual searches.