Ing. Michal Med, Ph.D.

Ontology learning from a text written in natural language is a well-studied domain. However, the applicability of techniques for ontology learning from natural language texts is strongly dependent on the characteristics of the text corpus and the language used. In this paper, we present our work so far in entity linking and enhancing the ontology with extracted relations between concepts. We discuss the benefits of adequately designed lexico-semantic patterns in ontology learning. We propose a preliminary set of lexico-semantic patterns designed for the Czech language to learn new relations between concepts in the related domain ontology in a semi-supervised approach. We utilize data from the urban planning and development domain to evaluate the introduced technique. As a partial prototypical implementation of the stack, we present Annotace, a text annotation service that provides links between the ontology model and the textual documents in Czech.

Implementing the INSPIRE directive involves transforming various data themes into the structure and content given by Data Specifications published by the Joint Research Center of the European Commission. The data is to be published in the GML format, which is the standard for the Open Geospatial Consortium. The validity of the data structure is ensured by validation against XML schemas. These schemas are usually also provided by JRC, though not necessarily for all application schemas. Six application schemas are defined for the currently implemented Buildings theme, but XML schemas are available for only three of them. All application schemas have been analyzed, and it has been found that the most suitable data model corresponds most closely to the BuildingsExtended2D application schema. No XML schema has been provided by JRC in the current version. The BuildingsExtendedBase abstract XML schema was also needed when using the previous schemas. There is now a need to create these missing XML schemas.

More than seven years ago, on the 14th March 2007, directive 2007/2/EC was signed. This Directive established Infrastructure for Spatial Information in the European Community – INSPIRE. It was transposed into the Czech legislation in 2009. Since then it is implemented. Directive dictates to create harmonised datasets containing spatial data divided into 34 themes and to publish those datasets via network services. Both datasets and services shall be provided with metadata records. In the Czech republic it is implemented primarily by the Czech Office for Surveying, Mapping and Cadastre, which has already implemented (or is currently implemening) following INSPIRE themes: Parcels, Addresses, Administrative Units, Buildings, Hydrography, Transportation Networks, Geographical names, Coordinate reference systems, Geographical grid systems, Protected sites and Elevation. Other subjects of the administration unfortunately aren't that active. The scope of this article focuses on the process of the preparation of data from databases on the ČÚZK, their transformation into the INSPIRE format and structure and the publication of datasets.