CEFAT4Cities, a Natural Language Layer for the ISA2 Core Public Service Vocabulary

CEFAT4Cities, a Natural Language Layer for the ISA2 Core Public Service Vocabulary Joachim Van den Bogaert, Arne Defauw, Sara Szoc, Frederic Everaert, Koen Van Winckel, Alina Kramchaninova, Anna Bardadym, Tom Vanallemeersch CrossLang Kerkstraat 106 9050 Gentbrugge Belgium {first.lastname}@croslang.com Abstract The CEFAT4Cities project (2020–2022) will create a “smart cities natural language context” (a software layer that facilitates the conversion of natural-language admin- istrative procedures, into machine-reada- ble data sets) on top of the existing ISA2 interoperability layer for public services. Integration with the FIWARE/ORION “Smart City” Context Broker, will make existing, paper-based, public services dis- coverable through “Smart City” frame- works, thus allowing for the development of more sophisticated and more user- friendly public services applications. An automated translation component will be included, to provide a solution that can be used by all EU Member States. As a result, the project will allow EU citizens and businesses to interact with public services on the city, national, regional and EU level, in their own language. 1 Introduction eGovernment tools and data sets provided by public sector organisations, are typically too fragmented across institutional levels and entities. This is known as the silo effect. To alleviate this effect, the ISA and ISA2 (Interoperability Solutions for European Public Administrations) programmes1 have been supporting the development of interoperability solutions for cross-border and cross-sector public services, for more than a decade. While ISA2 Actions, such as the Core Vocabularies and the Core Public 1 https://ec.europa.eu/isa2/isa2_en, ISA and ISA2 support the development of digital solutions that enable public administrations, businesses and Service Vocabulary Application Profile (CPSV- AP) provide public administrations with templates and tools for describing their public services in a uniform way, one important aspect is still missing, i.e. user-centredness: existing infrastructures are primarily designed to facilitate computer-to-computer interaction, using a common, machine-readable vocabulary. But EU citizens do not speak in standardized data fields. Instead, they use 24 official EU languages to talk to their government: for instance, for an Austrian national living in Belgium, and starting up a new business, it is more important to find an eGovernment procedure in his or her mother tongue, than to know that all data is represented in ISA2-compliant fields. 2 Proposed solution To speed up the development and adoption of multilingual, cross-border eGovernment services, the CEFAT4Cities project, which runs from April 2020 to March 2022, will build: • a quality-assured workflow that assists in transforming natural-language eGovernment administrative procedures into multilingual in- teroperable solutions. CEF eTranslation will be integrated as a tool for developing multilin- gual resources. • an open linked data repository containing the results of applying this workflow, i.e. multilin- gual vocabularies. • a FIWARE/ORION2 extension that allows the context broker to be integrated with the envis- aged workflow and resources. citizens in Europe to benefit from interoperable cross- border and cross-sector public services. 2 https://fiware- orion.readthedocs.io/en/master/ To promote the use of the CEFAT4Cities infra- structure within the smart cities community, a dis- semination and communication plan, along with a roadmap for future funding, will be …

Content truncated to 500 words