Skip to main content Skip to main navigation

Dr. Simon Ostermann

Organizational unit Multilinguality and Language Technology
Contact +49 681 85775 5310 (Saarbrücken)

https://simonost.github.io/home/
Address (Saarbrücken) Gebäude D3 1Stuhlsatzenhausweg 3D-66123 Saarbrücken

Publications

Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem

Qianli Wang; Tatiana Anikina; Nils Feldhus; Simon Ostermann; Sebastian Möller; Vera Schmitt

In: Marianna Apidianaki; Hend Al-Khalifa; Barbara Di Eugenio; Steven Schockaert (Hrsg.). 31th International Conference on Computational Linguistics 2025. International Conference on Computational Linguistics (COLING-2025), January 19-24, Abu Dhabi, United Arab Emirates, Association for Computational Linguistics, 2025.

To the publication

Common European Language Data Space.

Georg Rehm; Stelios Piperidis; Khalid Choukri; Andrejs Vasiļjevs; Katrin Marheinecke; Victoria Arranz; Aivars Bērziņ¨; Miltos Deligiannis; Dimitris Galanis; Maria Giagkou; Katerina Gkirtzou; Dimitris Gkoumas; Annika Grützner-Zahn; Athanasia Kolovou; Penny Labropoulou; Andis Lagzdiņ¨; Elena Leitner; Valérie Mapelli; Hélène Mazo; Simon Ostermann; Stefania Racioppa; Mickaël Rigault; Leon Voukoutis

In: Proceedings of the Language Resources and Evaluation Conference. International Conference on Language Resources and Evaluation (LREC-2024), May 20-25, Turin, Italy, ELRA, 2024.

To the publication

HybridBERT - Making BERT Pretraining More Efficient Through Hybrid Mixture of Attention Mechanisms

Gokul Srinivasagan; Simon Ostermann

In: Proceedings of the NAACL Student Research Workshop (SRW) 2024. NAACL-HLT Student Research Workshop (NAACL-SRW-2024), Association for Computational Linguistics, 2024.

To the publication
All publications

Profile

  • TRAILS

    Trustworthy and Inclusive Machines

    Natural language processing (NLP) has demonstrated impressive performance in some human tasks. To achieve such performance, current neural models need to be pre-trained on huge amounts of raw text…

    TRAILS

  • PERKS

    Eliciting and Exploiting Procedural Knowledge in Industry 5.0

    The PERKS project supports the holistic governance of industrial PK in its entire life cycle, from elicitation to management and from access to exploitation. PERKS bases its solutions on leading-edge…

    PERKS

  • DAM-S

    Semantische Suche für das "Meere Online"-Portal der Deutschen Allianz Meeresforschung

    Entwicklung einer semantischen, KI-gestützten Suchfunktion für das Portal "Meere Online" für die Deutsche Allianz Meeresforschung (DAM)

     

  • DisAI

    Improving scientific excellence and creativity in combating disinformation with artificial intelligence and language technologies

    In the DisAI project, the Kempelen Institute of Intelligent Technologies, DFKI, University of Copenhagen and CERTH joined forces to improve scientific excellence of KInIT in AI and language…

    DisAI

  • LT-Bridge

    Bridging the technology gap: Integrating Malta into European Research and Innovation efforts for AIbased language technologies

    The Horizon 2020 Work Programme Spreading Excellence and Widening Participation (WIDESPREAD) 2018-2020 states that the disparity in research and innovation capabilities between the leading EU Member…

    LT-Bridge
Show all projects