SyntaxFest 2025

Between 26 and 29 August, we hosted the international conference SyntaxFest 2025, co-organised by the Faculty of Arts, UL, FRI UL, and the Slovene Association for Language Technologies.

AI4DH team member Dr Kaja Dobrovoljc was the main organiser of the event. The symposium brought together five international conferences in the field of computational linguistics: the International Conference on Parsing Technologies, the Universal Dependencies Workshop, the International Conference on Dependency Linguistics, the Workshop on Treebanks and Linguistic Theories, and the Workshop on Quantitative Syntax, as well as two working meetings of COST UniDive (Universality, Diversity and Idiosyncrasy and Language Technology).

The event was attended by 135 international researchers from 34 countries. Eighty peer-reviewed scientific articles were presented and published in a collection of papers issued by the Association for Computational Linguistics (ACL). The conference included invited lectures by esteemed researchers in the field: understanding large language models (Isabel Papadimitriou, Harvard University), multilingual technologies (Miryam de Lhoneux, KU Leuven), standardisation of corpora (Daniel Zeman, Charles University), and corpus linguistics (Amir Zeldes, Georgetown University, and Xiaofei Lu, Pennsylvania State University).

AI4DH project coordinator Prof. Dr Marko Robnik-Šikonja gave a welcoming speech. Research team members presented their work on word order variation in spoken and written corpora, a comparative treebank analysis tool, and a toolkit for dependency (sub)tree extraction and analysis.

Explore photo highlights on the conference website.

Explore the collection of papers at this link.