Integration of automatic spatial annotations from different sources by means of semantic technologies

Resumo

Information Extraction is one of the main tasks in Text Mining, which is essential for all types of applications exploiting geographic information because there is a big volume of geographic information not directly compiled in specific formats proposed by Geographic Information Systems, but just embedded in plain text sources. Currently, there are several software solutions for the processing of texts and the annotation of spatial named entities. However, the problem of these tools is that their output is based on heterogeneous annotation languages, which make it difficult their integration in other systems.

The objective of this work is to propose the conversion of the output of these tools into a common spatial annotation language based on semantic technologies to facilitate their integration and interoperability. As a common annotation language we propose the use of a text annotation based on RDFa and using the vocabulary proposed by the international initiative Schema.org. In order to validate this proposal, we have created the necessary infrastructure to build a semantic repository of documents, where the annotations generated by different annotation tools can be integrated and harmonized.