Assisted Query Formulation using Normalised Word Vector and Dynamic Ontological Filtering Heinz Dreher, Robert Williams Curtin University of Technology, GPO Box U1987 Perth, Western Australia 6845 {Heinz.Dreher, Bob.Williams}@cbs.curtin.edu.au Abstract. Information seekers using the usual search techniques and engines are delighted by the sheer power of the technology at their command – speed, quantity. Upon closer inspection of the results, and reflection upon the next stages of the information seeking knowledge work, users are typically overwhelmed, and frustrated. We propose a partial solution by focusing on the query formulation aspect of the information seeking problem. First we introduce our version of a semantic analysis algorithm, named Normalised Word Vector, and explain its application in assisted query formulation. Secondly we introduce our ideas of supporting query refinement via Dynamic Ontological Filtering. 1 Introduction Information and Communications Technologies (ICT) pervade our society in which a growing proportion of the work is mental work (typically referred to as knowledge work) as opposed to physical work. The record of empowerment of physical workers through technology clearly shows the enormous benefit in terms of increased production, efficient and effective utilisation of resources, and greater safety for workers. Knowledge workers should expect to see similar gains in capacity, productivity, and in the quality of outputs, but progress in the empowerment of the knowledge worker needs a boost so that this promise and expectation can be realised. It is not so much a case of lack of vision: Neither the naked hand nor the understanding left to itself can effect much. It is by instruments and helps that the work is done, which are as much wanted for the understanding as for the hand. And as the instruments for the hand either give motion or guide it, so the instruments of the mind supply either suggestions for the understanding or cautions. [1]. More recently, by some three and a quarter centuries, Vannevar Bush [2] shared with us his vision of how research workers could be empowered with his MEMEX device. But despite the vision, and the tremendous advances in ICT, and their now pervasive nature, the knowledge worker is left languishing by and large. For example, whilst a literature search can now be conducted in a matter of days if not hours where only two decades ago it took weeks if not months, the researcher is confronted with millions upon millions of ‘hits’.