Atila Kaya

Multimedia Interpretation for Dynamic Ontology Evolution

The recent success of distributed and dynamic infrastructures for knowledge sharing has raised the need for semiautomatic/automatic ontology evolution strategies. Ontology evolution is generally defined as the timely adaptation of an ontology to changing requirements and the consistent propagation of changes to dependent artifacts. In this article, we present an ontology evolution approach in the context of multimedia interpretation. Ontology evolution in this context relies on the results obtained through reasoning for the interpretation of multimedia resources, through population of the ontology with new individuals or through enrichment of the ontology with new concepts and new semantic relations. The article analyses the results of interpretation, population and enrichment obtained in evaluation experiments in terms of measures such as precision and recall. The evaluation reveals encouraging results.

On ontology based abduction for text interpretation

Text interpretation can be considered as the process of extracting deep-level semantics from unstructured text documents. Deeplevel semantics represent abstract index structures that enhance the precision and recall of information retrieval tasks. In this work we discuss the use of ontologies as valuable assets to support the extraction of deep-level semantics in the context of a generic architecture for text interpretation.

Logical formalization of multimedia interpretation

Nowadays, many documents in local repositories as well as in resources on the web are multimedia documents that contain not only textual but also visual and auditory information. Despite this fact, retrieval techniques that relyonlyoninformation fromtextualsourcesare stillwidely used due to the success of current text indexing technology. However, to increase precision and recall ofmultimedia retrieval, the exploitation of information from all modalities is indispensable, and high-level descriptions of multimedia content are required. These symbolic descriptions, also called deep-level semantic annotations, play a crucial role in facilitating expressive multimedia retrieval. Even for text-based retrieval systems, deep-level descriptions of content are useful (see, e.g., [7]).