Joseph Cornelius

Joseph Cornelius is a researcher at IDSIA (Dalle Molle Institute for Artificial Intelligence) since September 2020. He holds a Bachelor's degree in Computer Science from Heinrich-Heine-University Düsseldorf and a Master's degree in Neural Systems and Computation from the University of Zurich and ETH Zurich. He worked as a research assistant at the Department of Computational Linguistics at the University of Zurich. His research interests comprise social media mining, automatic text summarization and natural language processing for the biomedical domain.

• LinkedIn
• semantic scholar

• Joseph Cornelius, Oscar Lithgow-Serrano, Sandra Mitrovic, Ljiljana Dolamic, and Fabio Rinaldi. 2024. BUST: Benchmark for the evaluation of detectors of LLM-Generated Text. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 8029–8057, Mexico City, Mexico. Association for Computational Linguistics.
• Joseph Cornelius, Oscar Lithgow-Serrano, Vani Kanjirangat, Fabio Rinaldi, Koji Fujimoto, Mizuho Nishio, Osamu Sugiyama, Ichikawa Kana, Nooralahzadeh Farhad, Aron N. Horvath, and Michael Krauthammer. "Leveraging Token-Based Concept Information and Data Augmentation in Few-Resource NER: ZuKyo-EN at the NTCIR-16 Real-MedNLP task." NTCIR, 2022.
• Oscar Lithgow-Serrano, Joseph Cornelius, Fabio Rinaldi, and Ljiljana Dolamic. "mattica@ SMM4H’22: Leveraging sentiment for stance & premise joint learning." Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task. 2022.
• Cornelius, Joseph, Tilia Ellendorff, and Fabio Rinaldi. "Approaching SMM4H with auto-regressive language models and back-translation." Proceedings of the Sixth Social Media Mining for Health (# SMM4H) Workshop and Shared Task. 2021.
• Joseph Cornelius, Tilia Ellendorff, Lenz Furrer, Fabio Rinaldi (2020). Aggregating and visualizing COVID-19 related social media mining. In: Proceedings of the 5th Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task, Barcelona, Spain, 8-13 December 2020
• Tilia Ellendorff, Joseph Cornelius, Heath Gordon, Nicola Colic and Fabio Rinaldi, UZH @ SMM4H: System Descriptions, Proceedings of the 2018 EMNLP Workshop SMM4H: The 3rd Social Media Mining for Health Applications Workshop and Shared Task, 2018, 56-60

E-Mail: joseph.cornelius AT idsia.ch

NLP group page