5 July 2026, by Janis-Marie Paul

Photo: HCDS/UHH

Researchers from the Hub of Computing and Data Science (HCDS) at the University of Hamburg are part of an international research team that has received two prestigious awards at the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2026) in San Diego.

The team's paper, "POLAR: A Benchmark for Multilingual, Multicultural, and Multi-Event Online Polarization," was recognized with the Best Paper Award at the 9th Workshop on Event Extraction and Understanding: Challenges and Applications (EEUCA 2026). In addition, the work received the Runner-Up Award in SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multi-event Online Polarization.

The POLAR benchmark addresses one of today's major challenges in Natural Language Processing (NLP): understanding online polarization across languages, cultures, and events. The dataset covers 22 languages and diverse cultural contexts, providing researchers with a valuable resource for developing and evaluating multilingual NLP systems capable of analysing complex societal discourse.

Researchers affiliated with HCDS and the University of Hamburg who contributed to the award-winning work include Robert Geislinger, Rudy Alexandro Garrido Veliz, Saba Anwar, Xintong Wang, Adem Chanie Ali, Martin Semmann, Chris Biemann, and Seid Muhie Yimam.

The awards highlight the importance of international collaboration in advancing trustworthy, multilingual AI and underscore the impact of HCDS research within the global computational linguistics community.

Congratulations to the entire international author team on this remarkable achievement!

Beyond these two awards, HCDS researchers contributed to several additional publications presented at ACL 2026, highlighting the strong international presence and broad research expertise of the University of Hamburg in Natural Language Processing and Artificial Intelligence.

Just Use XML: Revisiting Joint Translation and Label Projection. ACL Findings 2026. Thennal DK, Chris Biemann, Hans Ole Hatzel. 

CommonLID: Re-evaluating State-of-the-Art Language Identification Performance on Web Data (Suarez et al., ACL 2026)