Public administrations are aware of the advantages of sharing Open Government Data in terms of transparency, development of improved services, collaboration between stakeholders, and spurring new economic activities. Initiatives for the publication and interlinking of government service catalogs as Linked Open Data (LOD) support the interoperability among European administrations and improve the capability of foreign citizens to access services across Europe. However, linking service catalogs to reference LOD catalogs requires a significant effort from local administrations, preventing the uptake of interoperable solutions at a large scale. The web application presented in this paper is named CroSeR (Cross-language Service Retriever) and supports public bodies in the process of linking their own service catalogs to the LOD cloud. CroSeR supports different European languages and adopts a semantic representation of e-gov services based on Wikipedia. CroSeR tries to overcome problems related to the short textual descriptions associated to a service by embodying a semantic annotation algorithm that enriches service labels with emerging Wikipedia concepts related to the service. An experimental evaluation carried out on e-gov service catalogs in five different languages shows the effectiveness of our model.
Cross-language Semantic Retrieval and Linking of E-gov Services
NARDUCCI, FEDELUCIO;SEMERARO, Giovanni
2013-01-01
Abstract
Public administrations are aware of the advantages of sharing Open Government Data in terms of transparency, development of improved services, collaboration between stakeholders, and spurring new economic activities. Initiatives for the publication and interlinking of government service catalogs as Linked Open Data (LOD) support the interoperability among European administrations and improve the capability of foreign citizens to access services across Europe. However, linking service catalogs to reference LOD catalogs requires a significant effort from local administrations, preventing the uptake of interoperable solutions at a large scale. The web application presented in this paper is named CroSeR (Cross-language Service Retriever) and supports public bodies in the process of linking their own service catalogs to the LOD cloud. CroSeR supports different European languages and adopts a semantic representation of e-gov services based on Wikipedia. CroSeR tries to overcome problems related to the short textual descriptions associated to a service by embodying a semantic annotation algorithm that enriches service labels with emerging Wikipedia concepts related to the service. An experimental evaluation carried out on e-gov service catalogs in five different languages shows the effectiveness of our model.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.