Ontologies are developed to describe data semantics on the Semantic Web. Given the distributed nature and scale of the Semantic Web, a large number of ontologies with different terminologies and structures will be created to describe the same concepts and domains. Without semantic mapping, information fluidity within the Web could be blocked at the boundaries of these ontologies. Therefore, ont...

Mapping relational databases to RDF is a fundamental problem for the development of the Semantic Web. We present a solution, inspired by draft methods defined by the W3C where relational databases are directly mapped to RDF and OWL. Given a relational database schema and its integrity constraints, this direct mapping produces an OWL ontology, which, provides the basis for generating RDF instanc...

Zero-Shot Learning (ZSL) aims to classify a test instance from an unseen category based on the training instances from seen categories, in which the gap between seen categories and unseen categories is generally bridged via visual-semantic mapping between the low-level visual feature space and the intermediate semantic space. However, the visual-semantic mapping (i.e., projection) learnt based ...

Semantic integration remains a serious challenge in the context of the Semantic Web. Current research aims to solve this issue through the development of ontology mapping processes. However, there is a lack of rules and guidance for the use of those processes. This paper introduces an ontology mapping framework which covers the entire ontology mapping process from mapping discovery to mapping e...

We present an evaluation of inter-sentential coreference annotation in the context of manually created semantic networks. The semantic networks are constructed independently be each annotator and require an entity mapping priori to evaluating the coreference. We present the model used for mapping the semantic entities as well as the algorithm used for our evaluation task. We present the raw sta...

An architecture for implementing large scale holographic interconnections in photorefractive waveguides is described. Methods for controlling the hologram using unguided light are considered and experimentally demonstrated.

The tutoring process of conventional caseoriented medical training systems can be characterised as either guided or unguided. In contrast to that, the aim of the system "Docs'n Drugs" is to distinguish between different levels of guidance. The author can realise the tutoring case either as a guided, a half guided or a unguided tutoring process. The system architecture distinguishes between an a...

When facilitating interoperability at the data level one faces the problem that different data models are used as the basis for business formats. For example relational databases are based on the relational model, while XML Schema is basically a hierarchical model (with some extensions, like references). Our goal is to provide a syntax and a data model neutral format for the representation of b...

Zero-Shot Learning (ZSL) promises to scale visual recognition by bypassing the conventional model training requirement of annotated examples for every category. This is achieved by establishing a mapping connecting low-level features and a semantic description of the label space, referred as visual-semantic mapping, on auxiliary data. Reusing the learned mapping to project target videos into an...