NexusLinguarum is composed of five Working Groups (WGs) interoperating and providing mutual feedback between themselves, as shown in the Figure below, with WG1-WG3 working in close collaboration with WG4, and WG5 monitoring the cross-WG activities.

Working Groups in NexusLinguarum

The scientific work of the Action is being carried out over four years through several workshops and other scientific meetings organised by the WGs, and remote cooperation through electronic communication means (email, teleconference, etc.). STSMs will be organised within each WG, to promote synergies and maximize cooperation giving preference to Eearly Career Investigators (ECIs).

WG1 Linked data-based language resources
Objectives This WG aims to develop, evaluate and endorse best practices for the modelling, creation, evaluation, evolution, improvement, and enrichment of LLOD resources and data models.
Tasks
1.1 LLOD modelling
1.2 Creation and evolution of LLOD resources in a distributed and collaborative setting
1.3 Cross-lingual data interlinking, access and retrieval in LLOD
1.4 Improving and monitoring quality of LLOD sources
1.5 Development of the LLOD cloud for under-resourced languages and domains

 

WG2 Linked data-aware NLP services
Objectives This WG focuses on the application of linguistic data science methods including linked data to enrich NLP tasks in order to take advantage of the growing amount of linguistic (open) data available on the Web. The list of NLP tasks is not closed and others might be added at the request of the Action members or interested communities.
Tasks
2.1 LLOD in Knowledge extraction
2.2 LLOD in Machine Translation
2.3 LLOD in Multilingual Question Answering
2.4 LLOD in Word Sense Disambiguation and Entity Linking
2.5 LLOD in Terminology and Knowledge Management

 

WG3 Support for linguistic data science
Objectives WG3 aims to foster the study of linguistic data by following data analytic techniques at a large scale in combination with LLOD and linked data-aware NLP techniques.
Tasks
3.1 Big data and linguistic information
3.2 Deep learning and neural approaches for linguistic data
3.3 Linking structured multilingual language data across linguistic description levels
3.4 Multidimensional linguistic data.
3.5 Education in linguistic data science

 

WG4 Use cases and applications
Objectives This WG focuses on studying possible use cases and practical applications of the relevant technologies involved in the Action. Some relevant domains will be covered by this WG, but the list is not closed and others might be added at the request of the Action members or interested communities.
Tasks
4.1 Use cases in legal domain
4.2 Use cases in humanities and social sciences
4.3 Use cases in linguistics
4.4 Use cases in life sciences
4.5 Use cases in technology

 

WG5 Management and dissemination
Objectives WG5 takes care of the measures to be taken to ensure the creation of added value of the Action as a whole, to ensure its maximum visibility, and to monitor the cross-WG activities.
Tasks
5.1 Management
5.2 Cross-working group communication
5.3 Capacity building
5.4 External communication
5.5 Scientific publications strategy