5th Summer Datathon on Linguistic Linked Open Data (SD-LLOD-23)
The 5th Summer Datathon on Linguistic Linked Data (SD-LLOD-23) took place from took place from June 11th to June 16th at Castle Lužnica near Zagreb, Croatia. As in previous editions, the main idea behind SD-LLOD was to impart practical knowledge to individuals from both industry and academia, focusing on the application of Linked Open Data technology to Linguistics and Language Technology. One of the main focal points this year was the use of deep learning and neural approaches within the context of LLD.
The datathon brought together 32 student participants and 14 tutors and speakers. Marco Passarotti from the Università Cattolica del Sacro Cuore in Milan delivered the invited talk on the final day of the Datathon.
The participants were trained to:
- generate their own Linguistic Linked Data from existing data sources, using visual tools like VocBench and community standards like OntoLex lemon
- apply semantic technologies (linked data, knowledge graphs, RDF, SPARQL) to the field of language resources and learn about their benefits and applications for specific use cases
- explore the potential use of embeddings, machine learning, and deep learning techniques in combination with Linguistic Linked Data.
The datathon was organized to include both seminars covering theoretical aspects and discussions of selected topics, as well as hands-on sessions in which participants were guided in applying the methods and techniques through various practical assignments. The most valuable and, at the same time, the most demanding part of the schedule was devoted to datathon sessions, where participants worked in groups of 3 or 4 on their own mini-projects. In these projects, they had to apply what they had learned, involving the generation and/or use of Linguistic Linked Data.
On the final day of the Datathon, students had the opportunity to present the results of their projects. The best project award was presented to Slobodan Beliga, Ivana Filipović Petrović, Miguel Lopez Otal, and Yuliia Shpak for their work on “Croatian idioms in LLOD,” which was tutored by Manuel Fiorelli.
This edition of the Summer Datathon on LLOD will be remembered with particular fondness because it was the last Nexus event in which our beloved colleague, Thierry Declerck, participated. To say he “took part in it” is an understatement, as Thierry served as a tireless mentor to students while himself being eager to learn and listen to their ideas. It is a shared hope among all the participants that the Datathon will continue to gather exceptional tutors as well as talented, enthusiastic young people who, in the words of one participant, will “work on making our knowledge of this magical world linked”.