PMKI: an European Commission action for the interoperability, maintainability and sustainability of Language Resources

PMKI: an European Commission action for the interoperability, maintainability and sustainability of Language Resources Peter Schmitz, Enrico Francesconi*, Najeh Hajlaoui, Brahim Batouche Publications Office of the European Union, Luxembourg * Publications Office of the European Union, Luxembourg and ITTIG-CNR, Florence, Italy {Peter.Schmitz, Enrico.Francesconi}@publications.europa.eu {Najeh.Hajlaoui, Brahim.Batouche}@ext.publications.europa.eu Abstract The paper presents the Public Multilingual Knowledge Management Infrastructure (PMKI) action launched by the European Commission (EC) to promote the Digital Single Market in the European Union (EU). PMKI aims to share maintainable and sustainable Language Resources making them interoperable in order to support language technology industry, and public administrations, with multilingual tools able to improve cross border accessibility of digital services. The paper focuses on the main feature (interoperability) that represents the specificity of PMKI platform distinguishing it from other existing frameworks. In particular it aims to create a set of tools and facilities, based on Semantic Web technologies, to establish semantic interoperability between multilingual lexicons. Such task requires to harmonize in general multilingual language resources using standardised representation with respect to a defined core data model under an adequate architecture. A comparative study among the main data models for representing lexicons and recommendations for the PMKI service was required as well. Moreover, synergies with other programs of the EU institutions, as far as systems interoperability and Machine Translation (MT) solutions, are foreseen. For instance some interactions are foreseen between PMKI and MT service provided by the EC but also with other NLP applications. Keywords: Language Resources, Interoperability, Maintainability, Sustainability. 1. Introduction Language barriers in the EU make the European market fragmented and decrease its economic potential. The EU institutions aim to overcome language obstacles and increase cross-border e-commerce by building open multilingual tools and features free of charge. For this reason the European Commission, through the ISA2 program1, launched a pilot project on creating a public multilingual knowledge management infrastructure aimed to support e-commerce solutions in a multilingual environment. By creating interoperable multilingual classifications and terminologies, easily reusable by small and medium-sized enterprises (SMEs) and public administrations, the project aims to support services like machine translation, localisation and multilingual search. SMEs are currently at a disadvantage compared to big companies due to the high cost of providing multilingual services. In this respect PMKI aims to create a set of tools and facilities, based on semantic Web technologies, aimed to support enterprises, in particular the language technology industry, with multilingual tools in order to improve cross border accessibility of digital services and e-commerce solutions. In practical terms, overcoming language barriers on the Web means creating multilingual lexicons (as vocabularies, thesauri, taxonomies, semantic networks), establishing links between concepts, as well as using them to support the accessibility of services and goods offered through the Internet. This paper is organized as follows: in Section 2 the main objectives of PMKI are discussed; in Section 3 the foreseen interoperability solutions are illustrated; finally in Section 4 some conclusions are reported. 1 ISA2: Interoperability solutions for public administrations, businesses and citizens (https://ec.europa.eu/isa2/home_en ) 2. PMKI The objective …

Content truncated to 500 words