Skip to main content
European Commission logo print header

Ready-to-use Multilingual Linked Language Data for Knowledge Services across Sectors

Periodic Reporting for period 2 - Pret-a-LLOD (Ready-to-use Multilingual Linked Language Data for Knowledge Services across Sectors)

Berichtszeitraum: 2020-07-01 bis 2022-06-30

The Prêt-à-LLOD project is concerned with making linguistic linked open data ready-to-use and it is achieving this goal through three objectives: firstly through multilingual cross-sectoral data access based on our linguistic data portal, Linghub, and our license analysis system. Secondly, through making interoperable linguistic technology though our linking, transformation and workflow management systems and finally through providing sustainability of language resources to provide long-term access to both services and data. These goals are being demonstrated in four pilots associated with each of our commercial partners and showing the viability of these technologies in the areas of ICT, publishing, pharma and public services. As language technologies are increasingly becoming a part of the daily life of EU citizens, the project will provide direct benefits by making data for these language technologies more readily available and usable. In particular, the increase of data in minority languages will directly benefit speakers of these languages through Europe, ensuring that no citizens are left out of the digital revolution.
The project has successfully completed, achieving all its major milestones and deliverables.

The management of the project has proceeded successfully and the necessary communication and development methodologies have been put in place, include mailing lists, a web site, open-source code repositories, a data management plan and a software quality plan.

The commercial pilots were completed successfully and these pilots achieved the internal KPIs.

The research aspects of the project were highly successful as evinced by the many research publications that the project has produced.

The dissemination, communication and community-building aspects of the project have achieved spectacular success in the first year, with the project being well-represented at a large number of events as well as organizing successful innovation and community-building events. Unfortunately, the COVID pandemic caused significant issues with our dissemination strategy and we adapted by moving to online webinars.

In addition, the advisory board met on three occasions to provide feedback on the project in a virtual session. The first meeting was attended by Núria Bel, Florian Faes, Franciska de Jong and Gianfranco Cecconi. After the first meeting, Florian Faes decided to resign from the board and was replaced by José Manuel Goméz Pérez of Expert Systems for the next two meetings.
The project has achieved state-of-the-art results in several areas, including the development of new linking methodologies, the development of resources for minority languages and the creation of new platforms (such as Teanga and Fintan). The project organized the "Translation Inference Across Dictionaries" (TIAD) task that is leading to new tasks in multilingual linking and attracted much attention. The project has contributed very actively to the OntoLex model developed by the W3C community group and two new modules are planned to extend this standard and this work will contribute to the new LEXIDMA standard being developed by OASIS. The commercial partners have also had great success in combining research with commercially-relevant applications and have published papers, that in one case won a best paper award.
Project Logo