KUSCO


Knowledge Unsupervised Search for populating
Concepts on Ontologies

KUSCO is a system which aims to assign semantic annotations to places. These annotations are automatically extracted by applying natural language processing and information extraction techniques that have been thoroughly applied and tested using the World Wide Web as primary source. This process is formally named Semantic Enrichment of Places. In our case, we are particularly focused on extracting information that allows an interpreter to distinguish a place from other places that are spatially or conceptually close. In other words, the meaning of a place is a function of its most salient features, present in the textual descriptions found in on-line resources about that place. In our case, places correspond to Points Of Interest (POIs), as these are abundant in the Web. By definition, a POI is a place with meaning to someone and, if it is available on-line, it is likely that its interest is shared by many people. In our approach, we first crawl the Web to get a large quantity of POIs and then analyze each of them in order to obtain their individual Semantic Index: the set of words that best define each of them. Besides analyzing POIs, we also propose the application of such approach in several different contexts and we integrate them in a multi-faceted view of place.

Leave a Reply

Your email address will not be published. Required fields are marked *