Iryna Gurevych

Adjunct Professor of Natural Language Processing

Research interests

Gurevych’s main research interests are in machine learning for large-scale language understanding and text semantics, including multilingual representation learning and argument mining.

Email

Gurevych is professor of computer science and founder/director of the Ubiquitous Knowledge Processing (UKP) Lab at the Technical University (TU) of Darmstadt, Germany (40 full-time researchers). Gurevych’s outstanding work has received numerous awards. Examples are the ACL fellow award 2020 and the ever-first Hessian LOEWE Distinguished Chair award (2.5 million Euro) in 2021. Gurevych is co-director of the NLP program within ELLIS, a European network of excellence in machine learning. In 2023, she has become the president of the Association of Computational Linguistics (ACL).

In 2022, Gurevych was awarded one of the highly-coveted “ERC Advanced Grants” of 2.5 million euros from the European Research Council (ERC) for her project “InterText – Modeling Text as a Living Object in a Cross-Document Context”. The InterText project is creating the first-ever framework for exploring intertextuality in NLP. InterText develops conceptual and applied models and datasets for the study of inline commentary, implicit linking, and document versioning. The models are evaluated in two case studies involving academic peer review and conspiracy theory debunking.

Gurevych’s research contributes to NLP by providing efficient and effective NLP techniques that build on top of large language models, such as multilingual sentence embeddings or adapters. This allows to process and understand many languages, including the ones with few resources. In addition, her research removes critical limitations of current NLP which is unable to understand fine-grained relations between long and complex texts in context.

  • Ph.D. in computational linguistics from University of Duisburg-Essen, Germany
  • Diploma (distinction) in English and German linguistics from State University of Vinnytsia, Ukraine
  • Since 2022:  Member of the Berlin-Brandenburg Academy of Sciences and Humanities (BBAW), Technological Sciences Class
  • 2022: ERC Advanced Grant for the project “InterText – Modeling Text as a Living Object in a Cross-Document Context”, 2.5 Mil. Euro
  • 2021: First "LOEWE-Spitzenprofessur" (distinguished chair), awarded 2.5 Mil. Euro (2-3 awards per year across all disciplines in the federal state of Hesse)
  • 2020: ACL Fellow (<0,2% of the community) for outstanding work in Natural Language Processing and Machine Learning
  • 2008: Lichtenberg Interdisciplinary Professorship Award of the Volkswagen Foundation
  • 2007 to 2008: Three IBM UIMA Innovation Awards
  • 2007: Emmy-Noether Early Career Award of the German Research Foundation

Selected publications:

  • Iryna Gurevych, Michael Kohler and Gözde Gül Şahin. On the Rate of Convergence of a Classifier Based on a Transformer Encoder. In:IEEE Transactions on Information Theory,  68, Nr. 12, 2022, pp. 8139–8155.
  • Ilia Kuznetsov, Jan Buchmann, Max Eichler and Iryna Gurevych. Revise and Resubmit: An Intertextual Model of Text-based Collaboration in Peer Review. In: Computational Linguistics, Vol. 48, Nr. 4, 2022, pp. 949–986.
  • Gregor Geigle, Jonas Pfeiffer, Nils Reimers, Ivan Vulić and Iryna Gurevych.Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval. In: Transactions of the Association for Computational Linguistics, Vol. 10, 2022, pp. 503–521.
  • Ji-Ung Lee, Jan-Christoph Klie and Iryna Gurevych.Annotation Curricula to Implicitly Train Non-Expert Annotators. In: Computational Linguistics, Vol. 48, Nr. 2, 2022, pp. 343–373.
  • Michael Bugert, Nils Reimers and Iryna Gurevych.Generalizing cross-document event coreference resolution across multiple corpora. In: Computational Linguistics,  47, Nr. 3, 2021, pp. 575–614.
  • Iryna Gurevych, Judith Eckle-Kohler, and Michael Matuschek. Linked Lexical Knowledge Bases: Foundations and Applications. Synthesis Lectures on Human Language Technologies. Morgan & Claypool Publishers, July 2016. ISBN: 9781627059749.

Contact faculty affairs

Interested in working with our renowned faculty?
Fill out the below form and we will get back to you.