Marjan Čeh

Semantic Similarity Measures within the Semantic Framework of the Universal Ontology of Geographical Space

The objective of this paper is to discuss our methodology for comparing, searching and integrating geographic concepts. Searching for spatially oriented datasets could be illustrated by the complexity of the communication between the producer and user. The common vocabulary consists of a set of concepts describing the geographic space called universal ontology of geographical space (UOGS). We have defined the semantic parameters for measuring semantic similarities within the UOGS semantic framework and described our applicative approach to the similarity analyses of spatial databases. In order to test our results we have implemented the entire vocabulary as a set prolog fact. Following this we also implemented functionality such as the querying mechanism and the simple semantic similarity model, again as a set of prolog clauses. In addition to this, we applied prolog rules for the purpose of extracting semantic information describing geographic concepts and extracting it from natural language texts.

Evaluation of inductive logic programming for information extraction from natural language texts to support spatial data recommendation services

In this article we analyze a well-known and extensively researched problem: how to find all datasets, on the one hand, and on the other hand only those that are of value to the user when dealing with a specific spatially oriented task. In analogy with existing approaches to a similar problem from other fields of human endeavor, we call this software solution ‘a spatial data recommendation service.’ In its final version, this service should be capable of matching requests created in the users mind with the content of the existing datasets, while taking into account the users preferences obtained from the users previous use of the service. As a result, the service should recommend a list of datasets best suited to the users needs. In this regard, we consider metadata, particularly natural language definitions of spatial entities, a crucial piece of the solution. To be able to use this information in the process of matching the users request with the dataset content, this information must be semantically preprocessed. To automate this task we have applied a machine learning approach. With inductive logic programming (ILP) our system learns rules that identify and extract values for the five most frequent relations/properties found in Slovene natural language definitions of spatial entities. The initially established quality criterion for identifying and extracting information was met in three out of five examples. Therefore we conclude that ILP offers a promising approach to developing an information extraction component of a spatial data recommendation service.