Konstantin Todorov

Mining concept similarities for heterogeneous ontologies

We consider the problem of discovering pairs of similar concepts, which are part of two given source ontologies, in which each concept node is mapped to a set of instances. The similarity measures we propose are based on learning a classifier for each concept that allows to discriminate the respective concept from the remaining concepts in the same ontology. We present two new measures that are compared experimentally: (1) one based on comparing the sets of support vectors from the learned SVMs and (2) one which considers the list of discriminating variables for each concept. These lists are determined using a novel variable selection approach for the SVM. We compare the performance of the two suggested techniques with two standard approaches (Jaccard similarity and class-means distance). We also present a novel recursive matching algorithm based on concept similarities.

FUZZY ONTOLOGY ALIGNMENT USING BACKGROUND KNOWLEDGE

We propose an ontology alignment framework with two core features: the use of background knowledge and the ability to handle vagueness in the matching process and the resulting concept alignments. The procedure is based on the use of a generic reference vocabulary, which is used for fuzzifying the ontologies to be matched. The choice of this vocabulary is problem-dependent in general, although Wikipedia represents a general-purpose source of knowledge that can be used in many cases, and even allows cross language matchings. In the first step of our approach, each domain concept is represented as a fuzzy set of reference concepts. In the next step, the fuzzified domain concepts are matched to one another, resulting in fuzzy descriptions of the matches of the original concepts. Based on these concept matches, we propose an algorithm that produces a merged fuzzy ontology that captures what is common to the source ontologies. The paper describes experiments in the domain of multimedia by using ontologies containing tagged images, as well as an evaluation of the approach in an information retrieval setting. The undertaken fuzzy approach has been compared to a classical crisp alignment by the help of a ground truth that was created based on human judgment.

Ontology matching for the semantic annotation of images

The linguistic description, i.e. semantic annotation of images can benefit from representations of useful concepts and the links between them as ontologies. Recently, several multimedia ontologies have been proposed in the literature as suitable knowledge models to bridge the well known semantic gap between low level features of image content and its high level conceptual meaning. Nevertheless, these multimedia ontologies are often dedicated to (or initially built for) particular needs or a particular application. Ontology matching, defined as the process of relating different heterogeneous models, could be a suitable approach to solve several interoperability issues that coexist in semantic image annotation and retrieval. In this paper, we propose an original and generic instance-based ontology matching approach and a methodology to extract a minimal ontology defined as the common reference between different heterogeneous ontologies. Then, this approach is applied to two different semantic image retrieval issues: the bridging of the semantic gap by the matching of a multimedia ontology with a common-sense knowledge ontology and the matching of different multimedia ontologies to extract a common reference knowledge model dedicated to several multimedia applications.

A framework for a fuzzy matching between multiple domain ontologies

The paper proposes an alignment framework for a set of domain ontologies in order to enable their interoperability in a number of information retrieval tasks. The procedure starts by anchoring the domain ontologies concepts to the concepts of a generic reference ontology. This allows the representation of each domain concept as a fuzzy set of reference concepts or instances. Next, the domain concepts are mapped to one another by using fuzzy sets relatedness criteria. The match itself is presented as a fuzzy set of the reference concepts or instances, which allows the comparison of a new ontology directly to the already calculated matches. The paper contains a preliminary evaluation of the approach.

Extensional Ontology Matching with Variable Selection for Support Vector Machines

The paper builds on a previous finding of the same authors that concept similarity can be measured on the basis of small sets of characteristic features, selected separately and independently for every concept of two source ontologies. Extending a previously defined parameter-dependent similarity measure, the paper suggests the application of parameter-free correlation coefficients as concept similarity measures and compares their performance with the performance of the parametric similarity measure. An overall procedure for extensional ontology matching based on the suggested similarity criteria is proposed and empirically tested. In addition, the work includes an evaluation of a novel variable selection technique based on Support Vector Machines (SVMs).

Multimedia ontology matching by using visual and textual modalities

Ontologies have been intensively applied for improving multimedia search and retrieval by providing explicit meaning to visual content. Several multimedia ontologies have been recently proposed as knowledge models suitable for narrowing the well known semantic gap and for enabling the semantic interpretation of images. Since these ontologies have been created in different application contexts, establishing links between them, a task known as ontology matching, promises to fully unlock their potential in support of multimedia search and retrieval. This paper proposes and compares empirically two extensional ontology matching techniques applied to an important semantic image retrieval issue: automatically associating common-sense knowledge to multimedia concepts. First, we extend a previously introduced textual concept matching approach to use both textual and visual representation of images. In addition, a novel matching technique based on a multi-modal graph is proposed. We argue that the textual and visual modalities have to be seen as complementary rather than as exclusive sources of extensional information in order to improve the efficiency of the application of an ontology matching approach in the multimedia domain. An experimental evaluation is included in the paper.

Combining visual and textual modalities for multimedia ontology matching

Multimedia search and retrieval are considerably improved by providing explicit meaning to visual content by the help of ontologies. Several multimedia ontologies have been proposed recently as suitable knowledge models to narrow the well known semantic gap and to enable the semantic interpretation of images. Since these ontologies have been created in different application contexts, establishing links between them, a task known as ontology matching, promises to fully unlock their potential in support of multimedia search and retrieval. This paper proposes and compares empirically two extensional ontology matching techniques applied to an important semantic image retrieval issue: automatically associating common-sense knowledge to multimedia concepts. First, we extend a previously introduced matching approach to use both textual and visual knowledge. In addition, a novel matching technique based on a multimodal graph is proposed. We argue that the textual and visual modalities have to be seen as complementary rather than as exclusive means to improve the efficiency of the application of an ontology matching procedure in the multimedia domain. An experimental evaluation is included.