Tacit knowledge has long been recognised, however its research has focused largely on who is more likely to have this store of knowledge, rather than taking this one step further and elaborating on just how well this knowledge is diffused throughout the organisational domain. We focus our efforts on the IS organisational domain, by which we mean computing workplace professionals as opposed to t...

This dissertation addresses the problem of semi-automatically creating schema mappings. The need for developing schema mappings is a pervasive problem in many integration scenarios. Although the problem is well-known and a large body of work exists in the area, the development of schema mappings is today largely performed manually in industrial integration scenarios. In this thesis an approach ...

This paper investigates Locally Receptive Field Networks, a broad class of neural networks including Probabilistic Neural Networks and Radial Basis Function Networks, which naturally exhibit symbolic properties. Moreover, speciic attention is given to the sub-class of Fac-torizable Radial Basis Function Networks whose architecture can be directly translated into a propositional theory and vicev...

We present the findings of research conducted by way of a complete pilot study on two teams within an organisation we choose to label organisation X. Certainly from a knowledge management perspective, tacit knowledge is vital in preventing knowledge loss from skilled staff leaving the workplace and taking the ‘soft’ knowledge with them. More proficient means of capturing this knowledge by mappi...

This paper gives an overview of the mapping mechanism of SEAM-a methodology for the automatic generation of knowledge models and its mapping onto Java codes. It discusses the rules that will be used to map the different components in the knowledge model automatically onto Java classes, properties and methods. The aim of developing this mechanism is to help in the creation of a prototype which w...

This paper aims at supporting the knowledge engineering process by proposing an approach to map CommonKADS knowledge models into specifications based on the Production Rule Representation (PRR) language. This approach starts by proposing a metamodel of CommonKADS knowledge models. We define the concept of inference group, required to perform the mapping transformations, and an algorithm that id...

Text categorisation is challenging, due to the complex structure with heterogeneous, changing topics in documents. The performance of text categorisation relies on the quality of samples, effectiveness of document features, and the topic coverage of categories, depending on the employing strategies; supervised or unsupervised; single labelled or multi-labelled. Attempting to deal with these rel...

Knowledge graphs are useful resources for numerous AI applications, but they are far from completeness. Previous work such as TransE, TransH and TransR/CTransR regard a relation as translation from head entity to tail entity and the CTransR achieves state-of-the-art performance. In this paper, we propose a more fine-grained model named TransD, which is an improvement of TransR/CTransR. In Trans...