Skip to main content Skip to main navigation

MLT Headerbild© Adobe Stock

Multilinguality and Language Technology

E&E Group: Efficient and explainable NLP models

Modern NLP models and LLMs have specific flaws, despite being highly performant: First, they are black boxes: Parameters of proprietary models are not accessible at all; and even non-proprietary models are largely opaque in the sense that it is unclear where exactly specific knowledge is encoded in potentially billions of parameters. Second, there is a tendency to always increase the size of LLMs and training data to improve performance, which is especially problematic for domains or languages with fewer resources.

The E&E group of DFKI’s Research Department Multilinguality and Language Technology works on transparent and efficient NLP models. Our objective is to make the parameters and behaviour of LLMs more explainable and understandable to both end users and researchers. We try to improve LLMs with regard to data consumption, e.g. for domains or languages where data is scarce, by using structured data, new learning techniques, or other modalities; and in terms of model size, e.g. for settings where powerful hardware is not available.

We are involved in Twinning projects, where we provide knowledge transfer both on research topics and project management to newly established research institutions across Europe. We are involved in European procurement projects focusing on language resources, such as the European Language Resource Coordination and the Language Data Space.

Some current projects:

DisAI

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

Project Page

Fair Forward

Consulting services to Gesellschaft für Internationale Zusammenarbeit (GIZ) on technical aspects of AI in international cooperation including natural language processing (NLP), training data and data access for FAIR Forward – Artificial Intelligence for All. GIZ Project No. 19.2010.7-003.00

Project Page

PERKS

Eliciting and Exploiting Procedural Knowledge in Industry 5.0.

Project Page

TRAILS

Trustworthy and Inclusive Machines
Duration: 08/01/2024 - 07/31/2027

Project Page

Selected recent publications

  • Soft Language Prompts for Language Transfer
    Ivan Vykopal, Simon Ostermann, Marián Šimko
    In: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies. (Volume 1: Long Papers), pages 10294–10313. 2025.
  • GrEmLIn: A Repository of Green Baseline Embeddings for 87 Low-Resource Languages Injected with Multilingual Graph Knowledge
    Daniil Gurgurov, Rishu Kumar, Simon Ostermann
    In: Findings of the Association for Computational Linguistics: NAACL 2025, pages 1204–1221, Albuquerque, New Mexico. Association for Computational Linguistics. 2025.
  • Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem
    Qianli Wang, Tatiana Anikina, Nils Feldhus, Simon Ostermann, Sebastian Möller, Vera Schmitt
    In: Proceedings of the 31st International Conference on Computational Linguistics, pages 1150–1167. 2025.
  • HybridBERT - Making BERT Pretraining More Efficient Through Hybrid Mixture of Attention Mechanisms
    Gokul Srinivasagan and Simon Ostermann
    In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 285–291, Mexico City, Mexico. Association for Computational Linguistics. Runner-Up Best Paper Award.
  • Find-2-Find: Multitask Learning for Anaphora Resolution and Object Localization
    Cennet Oguz; Pascal Denis; Emmanuel Vincent; Simon Ostermann; Josef van Genabith
    In: Houda Bouamor; Juan Pino; Kalika Bali (Hrsg.). Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing (EMNLP), Singapore, Pages 8099-8110, Association for Computational Linguistics, 2023.
  • Investigating the Encoding of Words in BERT's Neurons Using Feature Textualization
    Tanja Bäumel; Soniya Vijayakumar; Josef van Genabith; Günter Neumann; Simon Ostermann
    In: Yonatan Belinkov; Sophie Hao; Jaap Jumelet; Najoung Kim; Arya McCarthy; Hosein Mohebbi (Hrsg.). Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP. Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP-2023), Singapore, Pages 261-270, Association for Computational Linguistics, 2023.