My name is Shorouq and I'm into machine learning and MLOps, NLP/NLU, and conversational AI. I'm currently working as a research engineer at RISE and at Uppsala University.
Previously a research assistant at Uppsala University within the LUVAL group.
ORCID: 0009-0007-2792-9345
- Jeanne Fernandez, Shorouq Zahra, Mariana Madruga de Brito, and Johanna Mård. 2026. Extracting information on public water shortages using news media and LLMs: a pilot study in Sweden. In Proceedings of the 3rd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2026), pages 99–115, Budapest, Hungary. Association for Computational Linguistics.
- Ni Li, Shorouq Zahra, Mariana Brito, Clare Flynn, Olof Görnerup, Koffi Worou, Murathan Kurfali, Chanjuan Meng, Wim Thiery, Jakob Zscheischler, Gabriele Messori, and Joakim Nivre. 2024. Using LLMs to Build a Database of Climate Extreme Impacts. In Proceedings of the 1st Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2024), pages 93–110, Bangkok, Thailand. Association for Computational Linguistics.
- Murathan Kurfalı, Shorouq Zahra, Evangelia Gogoulou, Luise Dürlich, Fredrik Carlsson, and Joakim Nivre. 2025. SweSAT-1.0: The Swedish University Entrance Exam as a Benchmark for Large Language Models. In Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025), pages 331–339, Tallinn, Estonia. University of Tartu Library.
- Murathan Kurfali, Shorouq Zahra, Joakim Nivre, and Gabriele Messori. 2025. ClimateEval: A Comprehensive Benchmark for NLP Tasks Related to Climate Change. In Proceedings of the 2nd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2025), pages 194–207, Vienna, Austria. Association for Computational Linguistics.
- Evangelia Gogoulou, Shorouq Zahra, Liane Guillou, Luise Dürlich, and Joakim Nivre. 2025. Can LLMs Detect Intrinsic Hallucinations in Paraphrasing and Machine Translation?. In Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM²), pages 161–177, Vienna, Austria and virtual meeting. Association for Computational Linguistics.
- (Preprint) A new set of tropical cyclone damage functions calibrated with the Wikimpacts 2.0 database and CLIMADA ensemble-of-strategies method
- N. Li, W. Thiery, S. Zahra, M. Madruga de Brito, K. Worou, M. Kurfalı, S. Lampe, P. Muñoz, C. Flynn, C. Trigoso, J. Nivre, J. Zscheischler, and G. Messori. 2026. Wikimpacts 1.0: a new global climate impact database based on automated information extraction from Wikipedia. Natural Hazards and Earth System Sciences, 26(6):2609--2636.
- Shorouq Zahra. 2020. Targeted Topic Modeling for Levantine Arabic. Master’s Thesis in Language Technology.
- Word Salad: detecting question evasion in political question–answer pairs by Jiawen, Hu. Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Languages, Department of Linguistics and Philology.
- Evaluation Robustness of Climate NLP Benchmarks: Revising SciDCC through Lexical Transformations in Multi-Label Scenarios by Stoykova, Yanitsa. Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Languages, Department of Linguistics and Philology.
